Thrust 5: Streetscape Applications
Design of an application services architecture that will enable the exploration of cross-layer or thrust optimizations and support novel streetscape applications.
Project 1: Human-Computer Interaction Design for Smart Streetscapes
Streetscape applications are fundamentally unique in their transparent integration within public spaces. They are not equipped with traditional displays, input mechanisms, or facilities to opt-in or opt-out. This creates an exciting new opportunity to reimagine human-computer interaction for this new class of system. CS3 is developing, piloting, and evaluating new interaction modalities to enable pedestrians to effectively engage with emerging streetscape applications.
This work explores optimal timing strategies for agent-human interaction in streetscape environments, focusing on seamless, context-aware interventions that enhance pedestrian engagement without disrupting natural movement. By leveraging insights from sensor data and real-time analytics, the system aims to identify precise moments for interaction, such as providing information or safety alerts, based on pedestrian speed, location, and environmental conditions. This approach helps create a more intuitive interface for public spaces, enhancing user experience and safety through minimally intrusive but timely interactions.
This work explores using large language models (LLMs) to analyze extensive urban datasets, demonstrated through a case study on NYC's 311 service requests. By combining data-driven insights with community narratives, the system aims to improve civic engagement and policymaking. Initial results with ChatGPT-4 highlighted challenges with recognizing long-term patterns due to context limitations. The paper suggests solutions, including narrative structure frameworks, spatiotemporal indexing, and fact-checking agents, to generate reliable, context-rich narratives. These enhancements aim to enable LLMs to provide meaningful urban insights, integrating personal experiences and structured data for better community-focused decision-making.
Project 2: Streetscape Application Stack and Runtime Design
Desktop and mobile applications benefit from robust execution substrates provided by underlying runtime platforms and application libraries and services. This has dramatically accelerated application development, broadened the community of developers, and provided performance and security benefits. CS3 is developing the equivalent platforms, libraries, and services for future streetscape applications. A key objective is to establish a new developer community anchored around these enabling (open-source) technologies.
Many CS3 applications will rely upon datasets that live beyond the administrative boundaries of the CS3 team. As one example, in the case of the Smart Intersection application, the application requires access to traffic data beyond the intersection instrumented by CS3. The team is developing standard toolsets to ingest, quality check, and integrate datasets like this (and beyond). Data from NYC department of transportation video streams, and from the Florida testbed is actively being integrated.
Robust decisions in streetscapes and related applications require high fidelity estimation of states and processes in the environment. This activity proposes communication-efficient distributed algorithms to combine sets of cooperative heterogeneous sensors under bandwidth limitation, with provable guarantees. The overarching goals are to manage limited communication bandwidth without suffering performance loss.
Many CS3 applications, including those designed by partners external to the team, depend only upon anonymized, synoptic information about the streetscape. Our Mobility Intelligence application, for example, is concerned only about the objects (e.g., pedestrians, scooters) and activities (e.g., walking, turning left) identified within the streetscape – not the specific characteristics of the participants (e.g., visual information). CS3 is developing a privacy-preserving scene and activity recognition pipeline that simplifies the development of these applications, including those built by external partners. This supports privacy preservation while broadening access for streetscape application developers.
This research is to develop a digital twin platform to support smart streetscape application testing. The digital twin platform is built based on high-resolution LiDAR or photogrammetry scan of the infrastructure and road environment. Trajectories of vehicles, pedestrians, and other road users generated from high-resolution LiDAR and computer vision sensors are used to reconstruct the real-world traffic conditions in the high-resolution infrastructure background. Key research problems lie in addressing the spatial-temporal synchronization and matching of multi-sensor data, predict and infer trajectory data due to line-of-sight coverage loss, and the next-generation traffic simulation models that can simulate high-fidelity traffic behavior in responses to the comprehensive 3D environment in the new digital twin models.
Project 3: Smart Streetscape Operating System or Hypervisor Design
The shift from dedicated computer and network systems (e.g., desktops) to shared-use computer and network systems (e.g., cloud) triggered important changes in the underlying operating systems and ushered in an era of system virtualization, enabling many logical systems to transparently share a smaller number of physical systems. The hypervisors that support this virtualization are a cornerstone of resource utilization efficiency and application scalability. CS3 is exploring new mechanisms –equivalent to components of modern operating systems and hypervisors— to extend these same benefits to future multi-tenant streetscape systems.
Implement a synchronization algorithm that aligns diverse sensors, including cameras and IMUs, to ensure consistent data integration for pedestrian safety applications.
Create a lightweight neural network, CoordinateTransformNet, to convert coordinates from different street-level cameras to a unified top-down view. This facilitates real-time integration of multiple camera feeds for comprehensive pedestrian and vehicle detection at intersections.
Utilize deep learning models such as YOLOv8 for object detection and OC-SORT for tracking. Fine-tune models for urban scenarios to handle various object sizes and complex dynamics, ensuring robust performance even during occlusions or temporary detection failures.
Recent Publications
5017967
rt5
1
modern-language-association
10
date
desc
2869
https://cs3-erc.org/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22B4V4VNKC%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Fan%20et%20al.%22%2C%22parsedDate%22%3A%222025-11-03%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BFan%2C%20Yuang%2C%20et%20al.%20%26%23x201C%3BPoster%3A%20Split-and-Combine%20Rectification%20of%20Ultra-Wide%20Fisheye%20Images%20into%20Cubemaps.%26%23x201D%3B%20%26lt%3Bi%26gt%3BProceedings%20of%20the%2031st%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%26lt%3B%5C%2Fi%26gt%3B%20%5BKerry%20Hotel%2C%20Hong%20Kong%20Hong%20Kong%20China%5D%2C%202025%2C%20pp.%201359%26%23x2013%3B61%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3680207.3765686%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3680207.3765686%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Poster%3A%20Split-and-Combine%20Rectification%20of%20Ultra-Wide%20Fisheye%20Images%20into%20Cubemaps%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuang%22%2C%22lastName%22%3A%22Fan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xuhai%22%2C%22lastName%22%3A%22Xu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaofan%22%2C%22lastName%22%3A%22Jiang%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222025-11-03%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2031st%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%22%2C%22conferenceName%22%3A%22ACM%20MOBICOM%20%2725%3A%2031st%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F3680207.3765686%22%2C%22ISBN%22%3A%22979-8-4007-1129-9%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F3680207.3765686%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-11-25T15%3A42%3A47Z%22%7D%7D%2C%7B%22key%22%3A%22FRRW6C6U%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Chen%20et%20al.%22%2C%22parsedDate%22%3A%222025-09-12%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BChen%2C%20Anjiang%2C%20et%20al.%20%26%23x201C%3BLiDAR%20Vehicle%20Trajectory%20Reconstruction%20with%20Arterial%20Shockwave%20Detection%20and%20Space%26%23x2013%3BTime%20Analysis.%26%23x201D%3B%20%26lt%3Bi%26gt%3BTransportation%20Research%20Record%26lt%3B%5C%2Fi%26gt%3B%2C%20Sept.%202025%2C%20p.%2003611981251357924%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F03611981251357924%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F03611981251357924%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22LiDAR%20Vehicle%20Trajectory%20Reconstruction%20with%20Arterial%20Shockwave%20Detection%20and%20Space%5Cu2013Time%20Analysis%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anjiang%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%20J.%22%2C%22lastName%22%3A%22Jin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tianya%20Terry%22%2C%22lastName%22%3A%22Zhang%22%7D%5D%2C%22abstractNote%22%3A%22Roadside%20LiDAR%20%28light%20detection%20and%20ranging%29%20sensors%20have%20become%20increasingly%20significant%20in%20collecting%20high-resolution%20trajectory%20data%20of%20vehicles%2C%20pedestrians%2C%20and%20other%20road%20users%2C%20supporting%20the%20deployment%20of%20connected%20and%20automated%20vehicle%20applications.%20These%20sensors%20operate%20effectively%20under%20various%20illumination%20and%20weather%20conditions%2C%20providing%20accurate%20three-dimensional%20positioning.%20However%2C%20the%20raw%20trajectory%20data%20often%20suffers%20from%20quality%20issues%2C%20such%20as%20missing%20segments%2C%20misaligned%20directions%2C%20inappropriate%20appearances%2C%20and%20sudden%20disappearances.%20These%20issues%20arise%20from%20field-of-view%20constraints%2C%20road%20user%20or%20infrastructure%20occlusions%2C%20and%20sensor%20or%20analytic%20engine%20limitations.%20To%20address%20these%20challenges%2C%20this%20paper%20presents%20a%20LiDAR%20trajectory%20reconstruction%20method%20that%20utilizes%20spatial-temporal%20analysis%20and%20shockwave%20detection%20to%20improve%20incomplete%20and%20noisy%20vehicle%20trajectories.%20The%20method%20includes%20a%20lane-based%20centerline%20map-matching%20algorithm%20to%20determine%20vehicle%20lane%20assignments%20and%20create%20lane-by-lane%20spatial-temporal%20trajectory%20diagrams.%20Fragmented%20trajectories%20are%20matched%20by%20analyzing%20their%20upstream%5Cu2013downstream%20continuation%20relationships.%20A%20shockwave%20detection%20technique%20is%20introduced%2C%20which%20assesses%20the%20convexity%20and%20concavity%20of%20each%20vehicle%20trajectory%20and%20identifies%20peaks%20in%20curvature.%20Finally%2C%20trajectories%20are%20stitched%20based%20on%20estimated%20vehicle%20states%20within%20regions%20separated%20by%20shockwaves.%20The%20proposed%20model%20was%20evaluated%20using%20roadside%20LiDAR%20trajectory%20data%20collected%20from%20two%20intersections%20during%20a%20workday%20in%20February%202024%20at%20the%20DataCity%20Smart%20Mobility%20Testing%20Ground%20in%20New%20Brunswick%2C%20New%20Jersey.%20The%20reconstruction%20results%20show%20promising%20performance%20in%20handling%20LiDAR%20coverage%20blind%20spots%20and%20accurately%20reconstructing%20shockwave%20patterns%2C%20as%20verified%20by%20field%20observations.%22%2C%22date%22%3A%222025-09-12%22%2C%22language%22%3A%22EN%22%2C%22DOI%22%3A%2210.1177%5C%2F03611981251357924%22%2C%22ISSN%22%3A%220361-1981%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F03611981251357924%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-09-15T14%3A19%3A07Z%22%7D%7D%2C%7B%22key%22%3A%22ILWCNR2E%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Nie%20et%20al.%22%2C%22parsedDate%22%3A%222025-06-09%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BNie%2C%20Jingping%2C%20et%20al.%20%26%23x201C%3BSoundTrack%3A%20A%20Contactless%20Mobile%20Solution%20for%20Real-Time%20Running%20Metric%20Estimation%20for%20Treadmill%20Running%20in%20the%20Wild.%26%23x201D%3B%20%26lt%3Bi%26gt%3BProceedings%20of%20the%20ACM%20on%20Interactive%2C%20Mobile%2C%20Wearable%20and%20Ubiquitous%20Technologies%26lt%3B%5C%2Fi%26gt%3B%2C%20vol.%209%2C%20no.%202%2C%20June%202025%2C%20pp.%201%26%23x2013%3B30%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3729486%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3729486%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22SoundTrack%3A%20A%20Contactless%20Mobile%20Solution%20for%20Real-time%20Running%20Metric%20Estimation%20for%20Treadmill%20Running%20in%20the%20Wild%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jingping%22%2C%22lastName%22%3A%22Nie%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuang%22%2C%22lastName%22%3A%22Fan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziyi%22%2C%22lastName%22%3A%22Xuan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minghui%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Runxi%22%2C%22lastName%22%3A%22Wan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthias%22%2C%22lastName%22%3A%22Preindl%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaofan%22%2C%22lastName%22%3A%22Jiang%22%7D%5D%2C%22abstractNote%22%3A%22Running%20metrics%20like%20cadence%20and%20ground%20contact%20time%20%28GCT%29%20are%20crucial%20for%20both%20novice%20and%20experienced%20runners%20to%20optimize%20performance%20and%20prevent%20injuries.%20We%20present%20SoundTrack%2C%20a%20contactless%20mobile%20solution%20that%20estimates%20these%20metrics%20by%20analyzing%20treadmill%20running%20sounds%20using%20on-device%20machine%20learning.%20Our%20main%20contributions%20are%3A%20%28i%29%20SoundTrackDB%20-%20a%20comprehensive%2040-hour%20dataset%20of%20treadmill%20running%20sounds%20collected%20from%2061%20subjects%20across%20363%20sessions%20in%2013%20public%20gyms%2C%20created%20in%20collaboration%20with%20a%20licensed%20running%20coach%3B%20and%20%28ii%29%20SoundTrack%20-%20an%20on-device%20mobile%20system%20capturing%20treadmill%20running%20sounds%2C%20mitigating%20noise%2C%20estimating%20cadence%20and%20GCT%20with%20a%20custom%20multi-layer%20perceptron%20%28MLP%29%20model%2C%20and%20providing%20real-time%20feedback.%20Microbenchmarks%20and%20evaluations%20show%20that%20SoundTrack%20effectively%20mitigates%20real-world%20noise%20challenges%20in%20public%20gyms%20and%20adapts%20to%20individual%20variations%20among%20runners%20and%20treadmill%20models.%20It%20achieves%20mean%20absolute%20percentage%20errors%20%28MAPEs%29%20of%201.62%25%20for%20cadence%20and%206.05%25%20for%20GCT%20on%20the%20test%20set%20of%20unseen%20running%20sessions%2C%20yielding%20results%20that%20are%20superior%20or%20comparable%20to%20commercial%20sports%20wearables.%20SoundTrack%20offers%20an%20accessible%20solution%20for%20treadmill%20metrics%20on%20mobile%20platforms%2C%20reducing%20reliance%20on%20specialized%20wearables%20and%20broadening%20accessibility.%20SoundTrackDB%2C%20SoundTrack%2C%20and%20the%20demonstration%20video%20are%20available%20at%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2FColumbia-ICSL%5C%2FSoundTrackDB.%22%2C%22date%22%3A%222025-06-09%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F3729486%22%2C%22ISSN%22%3A%222474-9567%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F3729486%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-06-26T18%3A03%3A35Z%22%7D%7D%2C%7B%22key%22%3A%22J22GIRXP%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Pargoo%20et%20al.%22%2C%22parsedDate%22%3A%222025-05-06%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BPargoo%2C%20Navid%20Salami%2C%20et%20al.%20%26%23x201C%3BUrban%20Sensing%20for%20Human-Centered%20Systems%3A%20A%20Modular%20Edge%20Framework%20for%20Real-Time%20Interaction.%26%23x201D%3B%20%26lt%3Bi%26gt%3BProceedings%20of%20the%203rd%20International%20Workshop%20on%20Human-Centered%20Sensing%2C%20Modeling%2C%20and%20Intelligent%20Systems%26lt%3B%5C%2Fi%26gt%3B%20%5BIrvine%20CA%20USA%5D%2C%202025%2C%20pp.%2092%26%23x2013%3B97%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3722570.3726890%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3722570.3726890%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Urban%20Sensing%20for%20Human-Centered%20Systems%3A%20A%20Modular%20Edge%20Framework%20for%20Real-Time%20Interaction%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Navid%20Salami%22%2C%22lastName%22%3A%22Pargoo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mahshid%22%2C%22lastName%22%3A%22Ghasemi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuren%22%2C%22lastName%22%3A%22Xia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mehmet%20Kerem%22%2C%22lastName%22%3A%22Turkcan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Taqiya%22%2C%22lastName%22%3A%22Ehsan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chengbo%22%2C%22lastName%22%3A%22Zang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuan%22%2C%22lastName%22%3A%22Sun%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Javad%22%2C%22lastName%22%3A%22Ghaderi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gil%22%2C%22lastName%22%3A%22Zussman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zoran%22%2C%22lastName%22%3A%22Kostic%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jorge%22%2C%22lastName%22%3A%22Ortiz%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222025-05-06%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%203rd%20International%20Workshop%20on%20Human-Centered%20Sensing%2C%20Modeling%2C%20and%20Intelligent%20Systems%22%2C%22conferenceName%22%3A%22SenSys%20%2725%3A%20The%2023rd%20ACM%20Conference%20on%20Embedded%20Networked%20Sensor%20Systems%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F3722570.3726890%22%2C%22ISBN%22%3A%22979-8-4007-1609-6%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F3722570.3726890%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-11-25T18%3A33%3A37Z%22%7D%7D%2C%7B%22key%22%3A%22GXPMABFB%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Mo%20et%20al.%22%2C%22parsedDate%22%3A%222025-01-03%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMo%2C%20Zhaobin%2C%20et%20al.%20%26%23x201C%3BSafeAug%3A%20Safety-Critical%20Driving%20Data%20Augmentation%20from%20Naturalistic%20Datasets.%26%23x201D%3B%20arXiv%3A2501.02143%2C%20arXiv%2C%203%20Jan.%202025%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2501.02143%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2501.02143%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22SafeAug%3A%20Safety-Critical%20Driving%20Data%20Augmentation%20from%20Naturalistic%20Datasets%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhaobin%22%2C%22lastName%22%3A%22Mo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yunlong%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xuan%22%2C%22lastName%22%3A%22Di%22%7D%5D%2C%22abstractNote%22%3A%22Safety-critical%20driving%20data%20is%20crucial%20for%20developing%20safe%20and%20trustworthy%20self-driving%20algorithms.%20Due%20to%20the%20scarcity%20of%20safety-critical%20data%20in%20naturalistic%20datasets%2C%20current%20approaches%20primarily%20utilize%20simulated%20or%20artificially%20generated%20images.%20However%2C%20there%20remains%20a%20gap%20in%20authenticity%20between%20these%20generated%20images%20and%20naturalistic%20ones.%20We%20propose%20a%20novel%20framework%20to%20augment%20the%20safety-critical%20driving%20data%20from%20the%20naturalistic%20dataset%20to%20address%20this%20issue.%20In%20this%20framework%2C%20we%20first%20detect%20vehicles%20using%20YOLOv5%2C%20followed%20by%20depth%20estimation%20and%203D%20transformation%20to%20simulate%20vehicle%20proximity%20and%20critical%20driving%20scenarios%20better.%20This%20allows%20for%20targeted%20modification%20of%20vehicle%20dynamics%20data%20to%20reflect%20potentially%20hazardous%20situations.%20Compared%20to%20the%20simulated%20or%20artificially%20generated%20data%2C%20our%20augmentation%20methods%20can%20generate%20safety-critical%20driving%20data%20with%20minimal%20compromise%20on%20image%20authenticity.%20Experiments%20using%20KITTI%20datasets%20demonstrate%20that%20a%20downstream%20self-driving%20algorithm%20trained%20on%20this%20augmented%20dataset%20performs%20superiorly%20compared%20to%20the%20baselines%2C%20which%20include%20SMOGN%20and%20importance%20sampling.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2501.02143%22%2C%22date%22%3A%222025-01-03%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2501.02143%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2501.02143%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-01-09T14%3A14%3A40Z%22%7D%7D%2C%7B%22key%22%3A%22ZBLGLGBL%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ge%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGe%2C%20Yi%2C%20et%20al.%20%26%23x201C%3BA%20Dynamic%20Blind%20Zone%20Simulation%20and%20Analysis%20Model%20for%20Roadside%20Light%20Detection%20and%20Ranging%20Sensor%20Deployment%20Considering%20the%20Full%20Roadway%20Terrain%20and%20Vehicle%20Dynamics.%26%23x201D%3B%20%26lt%3Bi%26gt%3BTransportation%20Research%20Record%3A%20Journal%20of%20the%20Transportation%20Research%20Board%26lt%3B%5C%2Fi%26gt%3B%2C%20vol.%202679%2C%20no.%207%2C%202025%2C%20pp.%20489%26%23x2013%3B518%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F03611981251327575%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1177%5C%2F03611981251327575%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22A%20Dynamic%20Blind%20Zone%20Simulation%20and%20Analysis%20Model%20for%20Roadside%20Light%20Detection%20and%20Ranging%20Sensor%20Deployment%20Considering%20the%20Full%20Roadway%20Terrain%20and%20Vehicle%20Dynamics%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yi%22%2C%22lastName%22%3A%22Ge%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%20J.%22%2C%22lastName%22%3A%22Jin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anjiang%22%2C%22lastName%22%3A%22Chen%22%7D%5D%2C%22abstractNote%22%3A%22Blind%20zones%20in%20light%20detection%20and%20ranging%20%28LiDAR%29%20sensors%20arise%20from%20their%20limited%20physical%20field%20of%20view%20and%20obstructions%20caused%20by%20static%20infrastructure%20or%20moving%20objects.%20Although%20originally%20intended%20for%20vehicle-based%20applications%2C%20LiDAR%20sensors%20are%20now%20increasingly%20deployed%20in%20roadside%20infrastructure%20for%20traffic%20monitoring%20and%20connected%20and%20automated%20vehicle%20safety%20and%20mobility%20applications.%20However%2C%20there%20is%20a%20dearth%20of%20robust%20tools%20for%20analyzing%20their%20detection%20range%2C%20resolution%2C%20and%20other%20characteristics%20in%20such%20settings.%20This%20study%20introduces%20a%20three-dimensional%20%283D%29%20blind%20zone%20simulation%20model%20for%20analyzing%20the%20detection%20characteristics%20of%20roadside%20LiDAR%20sensor%20deployment.%20The%20model%20replicates%20the%20impact%20of%20static%20infrastructure%20conditions%20and%20dynamic%20blind%20zones%20during%20live%20traffic.%20Initially%2C%20a%20real-world%20digital%20surface%20model%20%28DSM%29%20captures%203D%20data%20of%20road%20surfaces%20and%20obstructing%20infrastructure%20objects.%20Optical%20geometry%20models%20then%20assess%20blind%20zone%20severity%20across%20various%20roadway%20areas.%20Subsequent%203D%20vehicle%20shape%20and%20dynamic%20simulations%20evaluate%20blind%20zone%20distributions%20under%20typical%20traffic%20conditions.%20The%20model%5Cu2019s%20effectiveness%20is%20validated%20using%20field%203D%20point%20cloud%20data%20and%20vehicle%20detection%20data%20collected%20from%20a%20roadside%20LiDAR%20site%20on%20Route%2018%20in%20New%20Brunswick%2C%20NJ.%20Evaluation%20results%20demonstrate%20the%20model%5Cu2019s%20capability%20in%20analyzing%20complex%20static%20and%20dynamic%20blind%20zone%20distributions%2C%20offering%20insights%20for%20optimizing%20LiDAR%20sensor%20location%2C%20height%2C%20tilting%20angle%2C%20and%20manufacturer%20configuration%20parameters%20to%20minimize%20sensing%20blind%20zones.%20For%20code%20availability%2C%20see%5Cn%20%20%20%20%20%20%20%20%20%20%20%20%20%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Frutgerstslab%5C%2FLiDAR-Coverage-Analysis%5Cn%20%20%20%20%20%20%20%20%20%20%20%20%20%20.%22%2C%22date%22%3A%2207%5C%2F2025%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1177%5C%2F03611981251327575%22%2C%22ISSN%22%3A%220361-1981%2C%202169-4052%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fjournals.sagepub.com%5C%2Fdoi%5C%2F10.1177%5C%2F03611981251327575%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-11-25T18%3A41%3A38Z%22%7D%7D%2C%7B%22key%22%3A%22S4DUL8AN%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Zhang%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BZhang%2C%20Tianya%20Terry%2C%20et%20al.%20%26%23x201C%3BCar-Following%20Models%3A%20A%20Multidisciplinary%20Review.%26%23x201D%3B%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Intelligent%20Vehicles%26lt%3B%5C%2Fi%26gt%3B%2C%20vol.%2010%2C%20no.%201%2C%202025%2C%20pp.%2092%26%23x2013%3B116%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTIV.2024.3409468%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTIV.2024.3409468%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Car-Following%20Models%3A%20A%20Multidisciplinary%20Review%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tianya%20Terry%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peter%20J.%22%2C%22lastName%22%3A%22Jin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sean%20T.%22%2C%22lastName%22%3A%22McQuade%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexandre%22%2C%22lastName%22%3A%22Bayen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Benedetto%22%2C%22lastName%22%3A%22Piccoli%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%221%5C%2F2025%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTIV.2024.3409468%22%2C%22ISSN%22%3A%222379-8904%2C%202379-8858%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10547481%5C%2F%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222025-11-25T18%3A43%3A02Z%22%7D%7D%2C%7B%22key%22%3A%22VV28SSGL%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Moshfeghi%20and%20Jang%22%2C%22parsedDate%22%3A%222024-12-12%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMoshfeghi%2C%20Sonia%2C%20and%20Jinwoo%20Jang.%20%26%23x201C%3BPattern%20Mining%20of%20Older%20Drivers%26%23x2019%3B%20Driving%20Behavior%20Through%20Telematics-Data-Driven%20Unsupervised%20Learning.%26%23x201D%3B%2012%20Dec.%202024%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.36227%5C%2Ftechrxiv.173397871.10286123%5C%2Fv1%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.36227%5C%2Ftechrxiv.173397871.10286123%5C%2Fv1%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Pattern%20Mining%20of%20Older%20Drivers%27%20Driving%20Behavior%20Through%20Telematics-data-driven%20Unsupervised%20Learning%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sonia%22%2C%22lastName%22%3A%22Moshfeghi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jinwoo%22%2C%22lastName%22%3A%22Jang%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22%22%2C%22archiveID%22%3A%22%22%2C%22date%22%3A%222024-12-12%22%2C%22DOI%22%3A%2210.36227%5C%2Ftechrxiv.173397871.10286123%5C%2Fv1%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.techrxiv.org%5C%2Fusers%5C%2F822412%5C%2Farticles%5C%2F1250464-pattern-mining-of-older-drivers-driving-behavior-through-telematics-data-driven-unsupervised-learning%3Fcommit%3D741a4629abeda285b904939462884b6e4b4f70d2%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222024-12-20T19%3A57%3A37Z%22%7D%7D%2C%7B%22key%22%3A%22KRDEKGN3%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Nie%20et%20al.%22%2C%22parsedDate%22%3A%222024-12-04%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BNie%2C%20Jingping%2C%20et%20al.%20%26%23x201C%3BReal-Time%20Non-Contact%20Estimation%20of%20Running%20Metrics%20on%20Treadmills%20Using%20Smartphones.%26%23x201D%3B%20%26lt%3Bi%26gt%3BProceedings%20of%20the%2030th%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%26lt%3B%5C%2Fi%26gt%3B%20%5BWashington%20D.C.%20DC%20USA%5D%2C%202024%2C%20pp.%201644%26%23x2013%3B46%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3636534.3697446%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3636534.3697446%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Real-Time%20Non-Contact%20Estimation%20of%20Running%20Metrics%20on%20Treadmills%20using%20Smartphones%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jingping%22%2C%22lastName%22%3A%22Nie%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuang%22%2C%22lastName%22%3A%22Fan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziyi%22%2C%22lastName%22%3A%22Xuan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matthias%22%2C%22lastName%22%3A%22Preindl%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaofan%22%2C%22lastName%22%3A%22Jiang%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222024-12-04%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2030th%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%22%2C%22conferenceName%22%3A%22ACM%20MobiCom%20%2724%3A%2030th%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F3636534.3697446%22%2C%22ISBN%22%3A%229798400704895%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F3636534.3697446%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222024-12-12T16%3A33%3A56Z%22%7D%7D%2C%7B%22key%22%3A%22RFR84CIU%22%2C%22library%22%3A%7B%22id%22%3A5017967%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Liu%20et%20al.%22%2C%22parsedDate%22%3A%222024-12-04%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLiu%2C%20Yanchen%2C%20et%20al.%20%26%23x201C%3BSPECTRA%3A%20A%20Drone-Based%20Multispectral%20Sensing%20Platform%20for%20Complex%20Environment%20Perception.%26%23x201D%3B%20%26lt%3Bi%26gt%3BProceedings%20of%20the%2030th%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%26lt%3B%5C%2Fi%26gt%3B%20%5BWashington%20D.C.%20DC%20USA%5D%2C%202024%2C%20pp.%201742%26%23x2013%3B44%2C%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3636534.3698845%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F3636534.3698845%26lt%3B%5C%2Fa%26gt%3B.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22SPECTRA%3A%20A%20Drone-based%20Multispectral%20Sensing%20Platform%20for%20Complex%20Environment%20Perception%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yanchen%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Emily%22%2C%22lastName%22%3A%22Bejerano%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Minghui%22%2C%22lastName%22%3A%22Zhao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Federico%22%2C%22lastName%22%3A%22Tondolo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaofan%22%2C%22lastName%22%3A%22Jiang%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222024-12-04%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2030th%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%22%2C%22conferenceName%22%3A%22ACM%20MobiCom%20%2724%3A%2030th%20Annual%20International%20Conference%20on%20Mobile%20Computing%20and%20Networking%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F3636534.3698845%22%2C%22ISBN%22%3A%229798400704895%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F3636534.3698845%22%2C%22collections%22%3A%5B%22MNTPRDZV%22%5D%2C%22dateModified%22%3A%222024-12-10T14%3A19%3A30Z%22%7D%7D%5D%7D
Fan, Yuang, et al. “Poster: Split-and-Combine Rectification of Ultra-Wide Fisheye Images into Cubemaps.” Proceedings of the 31st Annual International Conference on Mobile Computing and Networking [Kerry Hotel, Hong Kong Hong Kong China], 2025, pp. 1359–61, https://doi.org/10.1145/3680207.3765686.
Chen, Anjiang, et al. “LiDAR Vehicle Trajectory Reconstruction with Arterial Shockwave Detection and Space–Time Analysis.” Transportation Research Record, Sept. 2025, p. 03611981251357924, https://doi.org/10.1177/03611981251357924.
Nie, Jingping, et al. “SoundTrack: A Contactless Mobile Solution for Real-Time Running Metric Estimation for Treadmill Running in the Wild.” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 9, no. 2, June 2025, pp. 1–30, https://doi.org/10.1145/3729486.
Pargoo, Navid Salami, et al. “Urban Sensing for Human-Centered Systems: A Modular Edge Framework for Real-Time Interaction.” Proceedings of the 3rd International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems [Irvine CA USA], 2025, pp. 92–97, https://doi.org/10.1145/3722570.3726890.
Mo, Zhaobin, et al. “SafeAug: Safety-Critical Driving Data Augmentation from Naturalistic Datasets.” arXiv:2501.02143, arXiv, 3 Jan. 2025, https://doi.org/10.48550/arXiv.2501.02143.
Ge, Yi, et al. “A Dynamic Blind Zone Simulation and Analysis Model for Roadside Light Detection and Ranging Sensor Deployment Considering the Full Roadway Terrain and Vehicle Dynamics.” Transportation Research Record: Journal of the Transportation Research Board, vol. 2679, no. 7, 2025, pp. 489–518, https://doi.org/10.1177/03611981251327575.
Zhang, Tianya Terry, et al. “Car-Following Models: A Multidisciplinary Review.” IEEE Transactions on Intelligent Vehicles, vol. 10, no. 1, 2025, pp. 92–116, https://doi.org/10.1109/TIV.2024.3409468.
Moshfeghi, Sonia, and Jinwoo Jang. “Pattern Mining of Older Drivers’ Driving Behavior Through Telematics-Data-Driven Unsupervised Learning.” 12 Dec. 2024, https://doi.org/10.36227/techrxiv.173397871.10286123/v1.
Nie, Jingping, et al. “Real-Time Non-Contact Estimation of Running Metrics on Treadmills Using Smartphones.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking [Washington D.C. DC USA], 2024, pp. 1644–46, https://doi.org/10.1145/3636534.3697446.
Liu, Yanchen, et al. “SPECTRA: A Drone-Based Multispectral Sensing Platform for Complex Environment Perception.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking [Washington D.C. DC USA], 2024, pp. 1742–44, https://doi.org/10.1145/3636534.3698845.
Researchers
Jorge Ortiz
Applications Research Lead; Assistant Professor of Electrical and Computer Engineering, Rutgers University
Jinwoo Jang
Assistant Professor Department of Civil, Environmental and Geomatics Engineering, Florida Atlantic University
Zoran Kostic
Professor of Professional Practice, Electrical Engineering, Columbia University
Sharon Di
Associate Professor of Civil Engineering and Engineering Mechanics, Columbia University
Valentine Aalo
Professor Department of Electrical Engineering and Computer Science, Florida Atlantic University
Trainees
Anton Rajko
SLC Institutional Representative; Undergraduate Student in Engineering, Florida Atlantic University
Mojtaba Jafarian Abyaneh
Ph.D. Student in Civil Engineering at Florida Atlantic University
Precious Nwaorgu
SLC Institutional Representative; PhD Student in Electrical Engineering, University of Central Florida
Qi Gao
Ph.D. Student in Civil Engineering and Engineering Mechanics at Columbia University
Sonia Moshfeghi
SLC Co-Chair; Ph.D. Student in Civil Engineering, Florida Atlantic University
Yongjie Fu
Ph.D. Student in Civil Engineering and Engineering Mechanics at Columbia University
