<p>In recent years, researchers have focused on the utilization of infrared images for object detection. Traditional object detection models rely on hand-crafted feature extractors, such as the Viola–Jones detector and Histogram of Oriented Gradients&#xa0;(HOG). However, these models often suffer from sluggish performance, limited accuracy, and poor adaptability to new datasets. Detecting objects from infrared images can be particularly challenging. To address this issue, modern approaches employ machine learning and deep learning techniques, with deep learning proving especially effective for large-scale image datasets. This paper provides a comprehensive review of various object detection architectures and their related techniques. A systematic review has been followed to summarize the current research work findings and discuss different research questions related to object detection, focusing on deep learning models that can detect objects from infrared images. Convolutional Neural Networks (CNNs), a subset of deep learning&#xa0;tools, are used for classifying infrared images. However, infrared images suffer from unique problems, including low contrast and non-uniformity.&#xa0;These problems may limit the performance of different object detectors, and hence the images may&#xa0;need special treatment in the form of pre-processing to allow successful object detection.</p>