There are several major challenges in detecting and recognizing multiple hidden objects from millimeter wave SAR security inspection images: inconsistent clarity of objects, similar objects, and complex background interference. To address these problems, a suspicious multi-object detection and recognition method based on the Multi-Path Extraction Network (MPEN) is proposed. In MPEN, You Only Look Once (YOLO) v3 is used as the base network, and then the Multi-Path Feature Pyramid (MPFP) module and modified residual block distribution are proposed. MPFP is designed to output the deep network feature layers separately. Then, to distinguish similar objects more easily, the residual block distribution is modified to improve the ability of the shallow network to capture details. To verify the effectiveness of the proposed method, the millimeter wave SAR images from the laboratory’s self-developed security inspection system are utilized in conducting research on multi-object detection and recognition. The detection rate (probability of detecting a target) and average false alarm (probability of error detection) rate of our method on the target are 94.6% and 14.6%, respectively. The mean Average Precision (mAP) of recognizing multi-object is 82.39%. Compared with YOLOv3, our method shows a better performance in detecting and recognizing similar targets.

There are several complex situations in recognizing concealed objects from millimeter wave multiple-input multiple-output synthetic aperture radar (MIMO-SAR) security images, such as incomplete imaging of objects, partially occluded objects, and overlapping objects, which are detrimental to the accurate recognition of concealed objects. To solve these problems, a concealed object detection method based on a high-resolution feature recursive alignment fusion network (HR-FRAFnet) is proposed. The HR-FRAFnet can segment the object area from the grayscale image with complex human background and complete the recognition. The overall architecture of the HR-FRAFnet follows the encoder-decoder framework. Specifically, in the encoder stage, a deep parallel feature extraction network (DPFEN) connects the multi-resolution feature maps in parallel and repeats multi-scale feature fusion. This approach suppresses the background noise flowing and retains more recognizable target characteristics. Then, in the decoder stage, a feature recursive alignment fusion module (FRAFM) is designed to enhance the perception of object edges. The FRAFM effectively improves the segmentation accuracy of objects whereas decreasing the computational complexity of the network. Besides, we employ a combined loss function to alleviate the foreground-background imbalance problem in MIMO-SAR images. Homemade human security screening image datasets are used for evaluation. The experimental results show that the proposed method outperforms existing semantic segmentation methods in Mean Intersection over Union (mIoU) and reduces the incidence of missed and error detection of targets.

There are several major challenges in the detection and identification of contraband in millimeter wave synthetic aperture radar (SAR) security images: the complexities of small target sizes, partially occluded targets, and overlap between multiple targets are not conducive to the accurate identification of contraband. To solve these problems, a contraband detection method based on the Dual Branch Multiscale Fusion Network (DBMFnet) is proposed. In the feature extraction stage, the feature extraction network is designed with a dual-branch parallel output structure. One branch preserves high-resolution while the other branch extracts rich semantic information through multiple downsampling operations. Bilateral connections are established between high-resolution and low-resolution branches to facilitate repeated feature exchange, which enhances the ability to detect small and fuzzy targets. In the feature fusion stage, a Multi-scale Fusion Module (MSFM) and a Context Aggregation Extraction Module (CAEM) are devised; MSFM is utilized to enhance target edge perception, and CAEM is employed to extract contextual information from low-resolution feature maps for enhancing model segmentation performance while reducing computational complexity. The experimental results show that the proposed semantic segmentation method outperforms existing semantic segmentation methods in mean intersection over union (mIoU).

With the rapid development of millimeter-wave technology in security inspection, its application in detecting contraband has demonstrated significant advantages. However, the low resolution, low pixel density, and unclear boundaries of terahertz images generated by millimeterwave imaging significantly limit the accurate detection of contraband. This paper proposes a Boundary-Enhanced Multi-Branch Network (BEMBNet) model based on a three-branch architecture. By designing a dedicated boundary branch and dynamic fusion modules, the model optimizes the extraction of target boundary features and the representation of global semantic information. The model efficiently integrates multi-scale features using Dynamic Reinforced Feature Pyramid Pooling (DRFPPM) and Boundary- Aware Multi-scale Fusion (BAMF) modules. Experiments demonstrate that BEMBNet outperforms existing advanced models across multiple metrics, particularly in low-resolution and boundary-blurred scenarios, exhibiting exceptional segmentation accuracy and computational efficiency. This research provides an innovative solution for millimeter-wave image processing and offers new directions for advancing security inspection technologies.