A systematic literature review on object detection using near infrared and thermal images

Significant advances have been achieved in object detection techniques using visible images for applications that include military operations, autonomous driving, and security surveillance. However, the quality of visible images suffers from various environmental and illumination conditions resulting in poor detection outcomes. To remedy this, a wide range of new methodologies using visual images together with infrared (IR) images of various wavelengths (including those referred to as thermal images) are being developed and presented to the open literature. Despite this progress, many challenges of object detection still prevail, and it is important to understand them. In this paper, we present a systematic literature review documenting recent advances in object detection using predominantly IR data. We discuss our systematic review process for the identification, filtering, screening, and selection of the relevant methodologies to include in the literature review. The selected methodologies are analyzed and organized into three main groups: (1) object detection in IR images, which includes detection of labeled objects, small target detection, and background subtraction, (2) object detection on multispectral data, and (3) data fusion approaches. Reviewed studies consider different types of objects, environmental conditions, and types of images, particularly in the IR domain. Finally, we discuss some of the key limitations of the current literature and opportunities for future research for improving object detection using both visible and IR data as well as LiDAR and radar data, when applicable. •Presents an analysis of recent advances in object detection using infrared data.•Uses an unsupervised learning approach (K-means) to cluster relevant studies.•Determines that multispectral techniques perform better in adverse conditions.•Identifies the need for standardized benchmarking using common datasets.