DAVE: A Unified Framework for Fast Vehicle Detection and Annotation
This work addresses the problem of efficient vehicle analysis for traffic surveillance, but it is incremental as it builds on existing CNN-based methods.
The paper tackles vehicle detection and annotation in streaming video for urban traffic surveillance by introducing DAVE, a unified framework that combines detection and attribute annotation using two jointly optimized CNNs, achieving consistent improvements over existing algorithms on multiple datasets.
Vehicle detection and annotation for streaming video data with complex scenes is an interesting but challenging task for urban traffic surveillance. In this paper, we present a fast framework of Detection and Annotation for Vehicles (DAVE), which effectively combines vehicle detection and attributes annotation. DAVE consists of two convolutional neural networks (CNNs): a fast vehicle proposal network (FVPN) for vehicle-like objects extraction and an attributes learning network (ALN) aiming to verify each proposal and infer each vehicle's pose, color and type simultaneously. These two nets are jointly optimized so that abundant latent knowledge learned from the ALN can be exploited to guide FVPN training. Once the system is trained, it can achieve efficient vehicle detection and annotation for real-world traffic surveillance data. We evaluate DAVE on a new self-collected UTS dataset and the public PASCAL VOC2007 car and LISA 2010 datasets, with consistent improvements over existing algorithms.