Sparse coding and improved dark channel prior-based deep CNN model for enhancing visibility of foggy images

Suganya, R.; Kanagavalli, R.

doi:10.1007/s41870-021-00742-7

Cited by 4 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vehicle detection in foggy weather is divided into two stages: defogging stage and vehicle detection stage. For the defogging stage, Suganya et al [9] proposed a sparse coding approach based on the dark channel prior algorithm to enhance the recovery of hazy sky images. Luo et al [10] introduced image defogging algorithm relies on compensating for various color wavelengths and utilizes the connection between transmittance and depth of field to provide a coarse estimation.…”

Section: Introductionmentioning

confidence: 99%

DCP-YOLOv7: dark channel prior image-dehazing YOLOv7 for vehicle detection in foggy scene

shuaiyin,

Fang

2023

Third International Conference on Computer Vision and Pattern Analysis (ICCPA 2023)

View full text Add to dashboard Cite

Aiming at the problem that the vehicle detection process in the foggy scene in automatic driving is vulnerable to the influence of fog, haze and other weather conditions, which causes a decrease in the quality of images captured by sensors, resulting in low accuracy of vehicle detection and positioning. This paper proposed a joint optimization scheme by combining DCP and YOLOV7 backbone detection networks called DCP-YOLOv7. This network consists of two modules: the image dehazing module DCP and the YOLOv7 detection module. Specifically, the DCP module performs image dehazing and YOLOv7 module performs vehicle detection. Experiments were conducted on the synthetic foggy VisDrone dataset to test the detection performance of DCP-YOLOv7. The results show that the mean Average Prediction (IoU=0.5) is 36.6% and 16.0% higher than that of SSD and Faster RCNN algorithm, reaching 86.7%, which can effectively detect vehicle object in foggy scenes.

show abstract

Section: Introductionmentioning

confidence: 99%