FFAVOD: Feature Fusion Architecture for Video Object Detection
| العنوان: | FFAVOD: Feature Fusion Architecture for Video Object Detection |
|---|---|
| المؤلفون: | Maguelonne Héritier, Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, business.industry, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 020207 software engineering, Advanced driver assistance systems, 02 engineering and technology, Object (computer science), Object detection, Artificial Intelligence, Feature (computer vision), Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), Code (cryptography), Redundancy (engineering), 020201 artificial intelligence & image processing, Computer vision, Computer Vision and Pattern Recognition, Artificial intelligence, business, Intelligent transportation system, Software |
| الوصف: | 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. Accepted for publication in Pattern Recognition Letters |
| اللغة: | English |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87d962b7cc5d79f5557e1f4466d7f1a3 http://arxiv.org/abs/2109.07298 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....87d962b7cc5d79f5557e1f4466d7f1a3 |
| قاعدة البيانات: | OpenAIRE |
كن أول من يترك تعليقا!