Application of image-to-image translation in improving pedestrian detection

TL;DR

This paper explores using image-to-image translation with deep learning models like pix2pixGAN and YOLOv7 on infrared-visible image pairs to enhance pedestrian detection in low-light conditions.

Contribution

It introduces a novel application of image-to-image translation techniques combined with object detection models for improved low-light pedestrian recognition.

Findings

Enhanced pedestrian detection accuracy in low-light scenes.

Effective use of infrared-visible image pairs for visual recognition.

Demonstrated feasibility of deep learning models in low-light conditions.

Abstract

The lack of effective target regions makes it difficult to perform several visual functions in low intensity light, including pedestrian recognition, and image-to-image translation. In this situation, with the accumulation of high-quality information by the combined use of infrared and visible images it is possible to detect pedestrians even in low light. In this study we are going to use advanced deep learning models like pix2pixGAN and YOLOv7 on LLVIP dataset, containing visible-infrared image pairs for low light vision. This dataset contains 33672 images and most of the images were captured in dark scenes, tightly synchronized with time and location.