FFAVOD: Feature Fusion Architecture for Video Object Detection

TL;DR

This paper introduces FFAVOD, a novel video object detection architecture that leverages feature sharing and fusion between consecutive frames to improve detection accuracy, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper presents a new architecture for video object detection that shares and fuses feature maps across frames, enhancing detection performance over existing methods.

Findings

Improved detection accuracy on multiple benchmarks.

Achieved state-of-the-art results on UA-DETRAC and UAVDT datasets.

Enhanced SpotNet with a new attention module.

Abstract

A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically 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 taking 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 object 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 object detectors on two object detection benchmarks containing sequences of moving road users. Additionally, to further increase performance, we propose an improvement to the SpotNet attention module. Using our architecture on the improved SpotNet detector, we obtain the state-of-the-art performance on the UA-DETRAC public benchmark as well as on the UAVDT dataset. Code is available at https://github.com/hu64/FFAVOD.