Hazing or Dehazing: the big dilemma for object detection

One of the biggest adversaries to the computer vision pipeline is bad weather which can deteriorate the visual quality of the captured images and lead to a decreased performance of tasks. Examples of such tasks can include image classification, object detection and semantic segmentation. To ameliorate this acquisition bottleneck, vision experts have developed restoration approaches which aim to recover the lost visual information due to the presence of poor climactic conditions such as atmospheric haze. The technique of single image dehazing has achieved great strides in producing aesthetically pleasing restorations to the human perception. However, it is important to establish whether these approaches bring the same merits to high-level vision tasks. To this end, we formulate a study around the task of object detection that aims to uncover the underlying relationship between this high-level task and atmospheric haze as well as examine the ability of the current dehazing process to enhance the detection performance. From our experiments we find that while there is a clear negative relationship between hazy conditions and detection performance, there is little help from the dehazing process to achieve the desired haze-free results.

I. Introduction

Every computer vision task begins with the acquisition of the images to be probed. The successful task execution and achievement of desired results is massively contingent on the quality that these image data possess, therefore, computer vision researches dedicate a great deal of effort to ensure the best possible level of quality. Bad weather is one of the biggest adversaries to vision experts as it cannot be mitigated during acquisition and can severely affect the quality of the input data. Environmental phenomena such as rain, mist, fog and haze can pose a great hindrance to the imaging pipeline.