skip to main content


Title: Traffic Video Event Retrieval via Text Query using Vehicle Appearance and Motion Attributes
Traffic event retrieval is one of the important tasks for intelligent traffic system management. To find accurate candidate events in traffic videos corresponding to a specific text query, it is necessary to understand the text query's attributes, represent the visual and motion attributes of vehicles in videos, and measure the similarity between them. Thus we propose a promising method for vehicle event retrieval from a natural-language-based specification. We utilize both appearance and motion attributes of a vehicle and adapt the COOT model to evaluate the semantic relationship between a query and a video track. Experiments with the test dataset of Track 5 in AI City Challenge 2021 show that our method is among the top 6 with a score of 0.1560.  more » « less
Award ID(s):
2025234
NSF-PAR ID:
10277269
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops
ISSN:
2160-7516
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Retrieving event videos based on textual description is a promising research topic in the fast-growing data field. Since traffic data increases every day, there is an essential need of an intelligent traffic system to speed up the traffic event search. We propose a multi-module system that outputs accurate results. Our solution considers neighboring entities related to the mentioned object to represent an event by rule-based, which can represent an event by the relationship of multiple objects. We also propose to add a modified model from last year's Alibaba model with an explainable architecture. As the traffic data is vehicle-centric, we apply two language and image modules to analyze the input data and obtain the global properties of the context and the internal attributes of the vehicle. We introduce a one-on-one dual training strategy for each representation vector to optimize the interior features for the query. Finally, a refinement module gathers previous results to enhance the final retrieval result. We benchmarked our approach on the data of the AI City Challenge 2022 and obtained the competitive results at an MMR of 0.3611. We were ranked in the top 4 on 50\% of the test set and in the top 5 on the full set. 
    more » « less
  2. Retrieving event videos based on textual description is a promising research topic in the fast-growing data field. Since traffic data increases every day, there is an essential need of an intelligent traffic system to speed up the traffic event search. We propose a multi-module system that outputs accurate results. Our solution considers neighboring entities related to the mentioned object to represent an event by rule-based, which can represent an event by the relationship of multiple objects. We also propose to add a modified model from last year's Alibaba model with an explainable architecture. As the traffic data is vehicle-centric, we apply two language and image modules to analyze the input data and obtain the global properties of the context and the internal attributes of the vehicle. We introduce a one-on-one dual training strategy for each representation vector to optimize the interior features for the query. Finally, a refinement module gathers previous results to enhance the final retrieval result. We benchmarked our approach on the data of the AI City Challenge 2022 and obtained the competitive results at an MMR of 0.3611. We were ranked in the top 4 on 50\% of the test set and in the top 5 on the full set. 
    more » « less
  3. In metropolitan areas with heavy transit demands, electric vehicles (EVs) are expected to be continuously driving without recharging downtime. Wireless Power Transfer (WPT) provides a promising solution for in-motion EV charging. Nevertheless, previous works are not directly applicable for the deployment of in-motion wireless chargers due to their different charging characteristics. The challenge of deploying in-motion wireless chargers to support the continuous driving of EVs in a metropolitan road network with the minimum cost remains unsolved. We propose CatCharger to tackle this challenge. By analyzing a metropolitan-scale dataset, we found that traffic attributes like vehicle passing speed, daily visit frequency at intersections (i.e., landmarks) and their variances are diverse, and these attributes are critical to in-motion wireless charging performance. Driven by these observations, we first group landmarks with similar attribute values using the entropy minimization clustering method, and select candidate landmarks from the groups with suitable attribute values. Then, we use the Kernel Density Estimator (KDE) to deduce the expected vehicle residual energy at each candidate landmark and consider EV drivers’ routing choice behavior in charger deployment. Finally, we determine the deployment locations by formulating and solving a multi-objective optimization problem, which maximizes vehicle traffic flow at charger deployment positions while guaranteeing the continuous driving of EVs at each landmark. Trace-driven experiments demonstrate that CatCharger increases the ratio of driving EVs at the end of a day by 12.5% under the same deployment cost. 
    more » « less
  4. Reconstructing 4D vehicular activity (3D space and time) from cameras is useful for autonomous vehicles, commuters and local authorities to plan for smarter and safer cities. Traffic is inherently repetitious over long periods, yet current deep learning-based 3D reconstruction methods have not considered such repetitions and have difficulty generalizing to new intersection-installed cameras. We present a novel approach exploiting longitudinal (long-term) repetitious motion as self-supervision to reconstruct 3D vehicular activity from a video captured by a single fixed camera. Starting from off-the-shelf 2D keypoint detections, our algorithm optimizes 3D vehicle shapes and poses, and then clusters their trajectories in 3D space. The 2D keypoints and trajectory clusters accumulated over long-term are later used to improve the 2D and 3D keypoints via self-supervision without any human annotation. Our method improves reconstruction accuracy over state of the art on scenes with a significant visual difference from the keypoint detector’s training data, and has many applications including velocity estimation, anomaly detection and vehicle counting. We demonstrate results on traffic videos captured at multiple city intersections, collected using our smartphones, YouTube, and other public datasets. 
    more » « less
  5. As a part of road safety initiatives, surrogate road safety approaches have gained popularity due to the rapid advancement of video collection and processing technologies. This paper presents an end-to-end software pipeline for processing traffic videos and running a safety analysis based on surrogate safety measures. We developed algorithms and software to determine trajectory movement and phases that, when combined with signal timing data, enable us to perform accurate event detection and categorization in terms of the type of conflict for both pedestrian-vehicle and vehicle-vehicle interactions. Using this information, we introduce a new surrogate safety measure, “severe event,” which is quantified by multiple existing metrics such as time-to-collision (TTC) and post-encroachment time (PET) as recorded in the event, deceleration, and speed. We present an efficient multistage event filtering approach followed by a multi-attribute decision tree algorithm that prunes the extensive set of conflicting interactions to a robust set of severe events. The above pipeline was used to process traffic videos from several intersections in multiple cities to measure and compare pedestrian and vehicle safety. Detailed experimental results are presented to demonstrate the effectiveness of this pipeline. 
    more » « less