计算机科学
目标检测
人工智能
管道(软件)
特征(语言学)
薄雾
领域(数学分析)
残余物
对象(语法)
计算机视觉
模式识别(心理学)
气象学
地理
算法
数学
哲学
数学分析
程序设计语言
语言学
作者
Vishwanath A. Sindagi,Poojan Oza,Rajeev Yasarla,Vishal M. Patel
摘要
Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images. To address this issue, we propose an unsupervised prior-based domain adversarial object detection framework for adapting the detectors to hazy and rainy conditions. In particular, we use weather-specific prior knowledge obtained using the principles of image formation to define a novel prior-adversarial loss. The prior-adversarial loss used to train the adaptation process aims to reduce the weather-specific information in the features, thereby mitigating the effects of weather on the detection performance. Additionally, we introduce a set of residual feature recovery blocks in the object detection pipeline to de-distort the feature space, resulting in further improvements. Evaluations performed on various datasets (Foggy-Cityscapes, Rainy-Cityscapes, RTTS and UFDD) for rainy and hazy conditions demonstrates the effectiveness of the proposed approach.
科研通智能强力驱动
Strongly Powered by AbleSci AI