A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth

TL;DR

This paper introduces a realistic, multi-view haze dataset with paired haze-free images and quantifiable haze levels, enabling better evaluation of vision algorithms in degraded outdoor environments.

Contribution

The first comprehensive haze benchmark dataset with controlled haze levels, paired images, and ground truth annotations for aerial and ground views.

Findings

Evaluated state-of-the-art dehazing methods on the dataset.

Assessed object detection performance in hazy conditions.

Provided a valuable resource for future research in scene understanding.

Abstract

Imagery collected from outdoor visual environments is often degraded due to the presence of dense smoke or haze. A key challenge for research in scene understanding in these degraded visual environments (DVE) is the lack of representative benchmark datasets. These datasets are required to evaluate state-of-the-art vision algorithms (e.g., detection and tracking) in degraded settings. In this paper, we address some of these limitations by introducing the first realistic hazy image benchmark, from both aerial and ground view, with paired haze-free images, and in-situ haze density measurements. This dataset was produced in a controlled environment with professional smoke generating machines that covered the entire scene, and consists of images captured from the perspective of both an unmanned aerial vehicle (UAV) and an unmanned ground vehicle (UGV). We also evaluate a set of representative state-of-the-art dehazing approaches as well as object detectors on the dataset. The full dataset presented in this paper, including the ground truth object classification bounding boxes and haze density measurements, is provided for the community to evaluate their algorithms at: https://a2i2-archangel.vision. A subset of this dataset has been used for the ``Object Detection in Haze'' Track of CVPR UG2 2022 challenge at http://cvpr2022.ug2challenge.org/track1.html.