A significant amount of redundancy exists between consecutive frames of a video. Object detectors typ-ically produce detections for one image at a time, without any capabilities for taking advantage of this redundancy. Meanwhile, many applications for object detection work with videos, including intelligent transportation systems, advanced driver assistance systems and video surveillance. Our work aims at tak -ing advantage of the similarity between video frames to produce better detections. We propose FFAVOD, standing for feature fusion architecture for video object detection. We first introduce a novel video ob-ject detection architecture that allows a network to share feature maps between nearby frames. Second, we propose a feature fusion module that learns to merge feature maps to enhance them. We show that using the proposed architecture and the fusion module can improve the performance of three base ob-ject detectors on two object detection benchmarks containing sequences of moving road users. Addi-tionally, to further increase performance, we propose an improvement to the SpotNet attention mod-ule. Using our architecture on the improved SpotNet detector, we obtain the state-of-the-art perfor-mance on the UA-DETRAC public benchmark as well as on the UAVDT dataset. Code is available at https://github.com/hu64/FFAVOD . (c) 2021 Elsevier B.V. All rights reserved.
展开▼
