CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
This work addresses the problem of limited data for traffic safety research, offering incremental improvements in pedestrian detection and accident forecasting for autonomous driving and surveillance applications.
The paper tackles the lack of public data for traffic accident analysis by introducing a novel CCTV dataset, and it improves pedestrian detection accuracy by integrating contextual information into Faster R-CNN, achieving up to +8.51% gains, while also demonstrating accident forecasting with an average Time-To-Accident of 1.684 seconds and 47.25% Average Precision.
This paper presents a novel dataset for traffic accidents analysis. Our goal is to resolve the lack of public data for research about automatic spatio-temporal annotations for traffic safety in the roads. Through the analysis of the proposed dataset, we observed a significant degradation of object detection in pedestrian category in our dataset, due to the object sizes and complexity of the scenes. To this end, we propose to integrate contextual information into conventional Faster R-CNN using Context Mining (CM) and Augmented Context Mining (ACM) to complement the accuracy for small pedestrian detection. Our experiments indicate a considerable improvement in object detection accuracy: +8.51% for CM and +6.20% for ACM. Finally, we demonstrate the performance of accident forecasting in our dataset using Faster R-CNN and an Accident LSTM architecture. We achieved an average of 1.684 seconds in terms of Time-To-Accident measure with an Average Precision of 47.25%. Our Webpage for the paper is https://goo.gl/cqK2wE