Detection of Small Moving Targets in Cluttered Infrared Imagery

Deep convolutional neural networks can achieve remarkable results for detecting and recognizing large- and medium-sized objects in visible band color images. However, the ability to detect small objects has yet to achieve the same level of performance. Our focus is on applications that require the accurate detection and localization of small moving objects that are distant from the sensor. State-of-the-art object detection and classification networks (such YOLOv3 and mask region-based CNN) are not well suited for finding small moving objects in infrared imagery, nor do they handle temporal information in video sequences. To overcome the limitations of these methods, we propose the moving target indicator network (MTINet), a new model specifically designed for detecting small moving targets in clutter. Several versions of the MTINet are presented with different refinements (such as spatial pyramid blocks and improved attention mechanism) to increase the probability of detection and reduce false alarm rates. The MTINet is trained to maximize the target to clutter ratio (TCR) metric, which represents the first use of the TCR loss function for detecting moving objects. To further challenge the MTINet, we also evaluated its performance with simulated sensor movement mimicking effects of image stabilization processes. Finally, we also propose a modification of the Reed-Xiaoli detector (originally developed for anomaly detection in hyperspectral data) to enable it to detect temporal anomalies caused by moving objects and refer to it as the temporal anomaly Reed-Xiaolis (t-ARX) algorithm. We find that the t-ARX algorithm can achieve better probability of detection at lower false alarm rates, while the MTINet is superior at finding difficult targets at higher false alarm rates. We then show that the combination of the two algorithms achieves the best overall performance.