A Vision-Based Video Crash Detection Framework for Mixed Traffic Flow Environment Considering Low-Visibility Condition

Abstract

In this paper, a vision-based crash detection framework was proposed to quickly detect various crash types in mixed traffic flow environment, considering low-visibility conditions. First, Retinex image enhancement algorithm was introduced to improve the quality of images, collected under low-visibility conditions (e.g., heavy rainy days, foggy days and dark night with poor lights). Then, a Yolo v3 model was trained to detect multiple objects from images, including fallen pedestrians/cyclists, vehicle rollover, moving/stopped vehicles, moving/stopped cyclists/pedestrians, and so on. Then, a set of features were developed from the Yolo outputs, based on which a decision model was trained for crash detection. An experiment was conducted to validate the model framework. The results showed that the proposed framework achieved a high detection rate of 92.5%, with relatively low false alarm rate of 7.5%. There are some useful findings: (1) the proposed model outperformed empirical rule-based detection models; (2) image enhancement method can largely improve crash detection performance under low-visibility conditions; (3) the accuracy of object detection (e.g., bounding box prediction) can impact crash detection performance, especially for minor motor-vehicle crashes. Overall, the proposed framework can be considered as a promising tool for quick crash detection in mixed traffic flow environment under various visibility conditions. Some limitations are also discussed in the paper.

AI Enabled Accident Detection and Alert System Using IoT and Deep Learning for Smart Cities

“…This system only detects accidents and does not consider the rescue operations. C. Wang et al [29] introduced a computer vision-based accident detection and rescue system. The pre-trained Yolo v3 model was used for accident identification.…”

Detection and Recognition of Car Plates in Parking Lots at Baghdad University

“…Recently, a significant focus has been on car license plate discovery and recognition technologies [1,2], which include traffic violations and tolls to accident monitoring, vehicle health checks, traffic monitoring, stolen vehicle detection, gate control, etc. [3]. Due to the variety of conditions and types of license plates, the capacity to automatically detect and recognize plates is one of the essential instruments employed by police department organizations worldwide.…”

Research on video image stabilization decision algorithm based on ROI block matching method

“…In automobile collision experiments, due to the huge impact force generated when a collision occurs, it is very easy to cause high-speed camera shaking, and this undesired shaking will seriously affect the feasibility and accuracy of subsequent image analysis and cannot meet the requirements of complete and clear image information acquisition, which directly affects the effect of automobile safety technology development and test verification and causes significant economic losses [1,2] .…”