A high-performance approach to detecting small targets in long-range low-quality infrared videos
| Autor: | Bence Budavari, Chiman Kwan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Connected component
Computer science business.industry Detector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020206 networking & telecommunications 02 engineering and technology Display resolution Tracking (particle physics) Signal Processing 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Range (statistics) sort 020201 artificial intelligence & image processing Computer vision Artificial intelligence Electrical and Electronic Engineering F1 score business |
| Zdroj: | Signal, Image and Video Processing. 16:93-101 |
| ISSN: | 1863-1711 1863-1703 |
| Popis: | Since targets are small in long-range infrared (IR) videos, it is challenging to accurately detect targets in those videos. In this paper, we propose a high-performance approach to detecting small targets in long-range and low-quality infrared videos. Our approach consists of a video resolution enhancement module, a proven small target detector based on local intensity and gradient (LIG), a connected component (CC) analysis module, and a track association module known as Simple Online and Real-time Tracking (SORT) to connect detections from multiple frames. Extensive experiments using actual mid-wave infrared (MWIR) videos in range between 3500 and 5000 m from a benchmark dataset clearly demonstrated the efficacy of the proposed approach. In the 5000 m case, the F1 score has been improved from 0.936 without SORT to 0.977 with SORT. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink