For the extremely small size and low signal‐to‐clutter ratio, target detection in infrared images is still a considerable challenge. Specifically, it is very difficult to detect the point targets because there is no texture and shape information can be used. A target‐oriented shallow‐deep feature‐based detection algorithm is proposed, opening up a promising direction for convolutional neural network‐based infrared dim small target detection algorithms. To ensure that small target instances can be used correctly for networks, the effective small anchor is designed according to the shallow layer of ResNet50. To determine whether a detection result belongs to the target, the authors depend on whether the detection centre is included in the ground truth area, rather than on the Intersection Over Union overlap rate, which avoids misjudging the detection result. In this way, small targets can be trained and detected correctly through ResNet50. More importantly, the authors demonstrate that spatially finer shallow features are crucial for small target detection and that semantically stronger deep features are helpful for improving detection probability. Experimental results on simulation data sets and real data sets show that the proposed algorithm can detect the point target when the local signal‐to‐clutter ratio is approximately 1.3, displaying infinite advantage and great potentiality.
Object discrimination plays an important role in an infrared (IR) imaging system. However, at a long observing distance, the presence of detector noise and the absence of robust features make space objects' discrimination difficult to tackle with. In this paper, a multi-scale convolutional neural network (MCNN) is proposed for feature learning and classification. It consists of three parts: transformation, local convolution, and full convolution. Different from previous objects' classification methods, the MCNN can automatically extract features of objects at multi-timescales and multi-frequencies. Low-level features are combined with high-level features to simultaneously capture long-term tendency and short-term fluctuations of the time sequences of IR radiation intensity. Training data are generated from IR radiation models considering micro-motion dynamics and inherent properties of space point objects under different scenarios. The simulation results indicate that our method not only promotes the performance but is also robust to the detector noise. The classification accuracy can reach 96% at a strong noise level (signal-to-noise ratio is 10 dB) in a simulation scenario. INDEX TERMS Convolutional neural network, space point objects, infrared radiation, discrimination, multi-scale.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.