An innovative and improved method for infrared object detection is proposed, aiming to enhance the capabilities of the YOLOv8 model. This approach specifically addresses the model’s inherent limitations by integrating the Convolutional Block Attention Module (CBAM), which enhances feature discrimination through attention mechanisms. By focusing on the most relevant features in the infrared images, CBAM allows the model to make more accurate detections. Additionally, the method incorporates CLAHE (Contrast Limited Adaptive Histogram Equalization) as a preprocessing step. This technique significantly improves the overall interpretability of infrared images by enhancing contrast and making subtle features more visible. The combination of CBAM and CLAHE enables the model to better handle the challenges posed by infrared imaging, such as low contrast and noise. The mAP@0.5 obtained during this study for our adopted methodology is better than YOLO8, however the statistics stand at lower values of at 20.2 and 29.5% respectively.