去模糊
人工智能
计算机科学
预处理器
计算机视觉
对比度(视觉)
目标检测
数学形态学
低分辨率
图像(数学)
图像处理
模式识别(心理学)
高分辨率
图像复原
地理
遥感
作者
Maxence Chaverot,Maxime Carré,Michel Jourlin,Abdelaziz Bensrhair,R. Grisel
出处
期刊:Integrated Computer-aided Engineering
[IOS Press]
日期:2023-07-10
卷期号:: 1-15
摘要
Thermal images are widely used for various applications such as safety, surveillance, and Advanced Driver Assistance Systems (ADAS). However, these images typically have low contrast, blurred aspect, and low resolution, making it difficult to detect distant and small-sized objects. To address these issues, this paper explores various preprocessing algorithms to improve the performance of already trained object detection networks. Specifically, mathematical morphology is used to favor the detection of small bright objects, while deblurring and super-resolution techniques are employed to enhance the image quality. The Logarithmic Image Processing (LIP) framework is chosen to perform mathematical morphology, as it is consistent with the Human Visual System. The efficacy of the proposed algorithms is evaluated on the FLIR dataset, with a sub-base focused on images containing distant objects. The mean Average-Precision (mAP) score is computed to objectively evaluate the results, showing a significant improvement in the detection of small objects in thermal images using CNNs such as YOLOv4 and EfficientDet.
科研通智能强力驱动
Strongly Powered by AbleSci AI