Active Millimeter Wave Research Articles

Enhancing concealed object detection in Active Millimeter Wave Images using wavelet transform

In contemporary security detection systems, the utilization of millimeter-wave radar has assumed a central role owing to its non-contact and innocuous nature. This study addresses the challenging issues of detecting low-resolution and small targets in active millimeter wave (AMMW) images concealed detection. We identify a prevalent drawback in existing detectors, specifically the adoption of strided convolution or pooling layers, leading to a loss of crucial details that adversely impacts the detection rate. To overcome this limitation, we introduce a novel convolutional structure, termed Wavelet-Conv, which maintains information integrity while segregating features from high and low frequency bands, effectively replacing the unfavorable design. Furthermore, we harness the wavelet transform to enhance channel and spatial attention mechanisms, enabling more effective utilization of frequency band features and ensuring interpretability in the computational process. In this pursuit, we integrate the proposed Wavelet-Conv and Wavelet-Attention modules into the YOLOv8 framework, culminating in a unified model, termed Wavelet-YOLO. Through rigorous experimental validation on two AMMW datasets, our approach exhibits superior performance by significantly enhancing the recall and mean average precision (mAP) of small targets in AMMW images, while maintaining competitive inference speed. Extensive experiments demonstrate the outperformance of our proposed method over existing state-of-the-art approaches.

Precise Localization of Concealed Objects in Millimeter-Wave Images via Semantic Segmentation

Existing concealed objects detection methods in active millimeter wave (AMMW) images are mainly based on bounding boxes. In this paper, we consider the problem of precise localization of concealed objects in AMMW images with the use of semantic segmentation networks. To improve the performance of the detection and localization of concealed objects, we propose a method with two steps. In the first step, we build a two-class semantic segmentation network to segment concealed objects in pixels from the images with the complex human body background, while in the second step, we use connected components extraction to detect and localize concealed objects in the segmented image. To improve the performance of the detection and localization of small objects, the network we built is composed of stacked dilated convolution blocks to enlarge the receptive field while keeping the resolution of associated feature maps unchanged. In addition, we give a rule for design of the associated dilation rates and the expand-contract dilation (ECD) assignment strategy for the pattern of the dilation rates. In the numerical experiments, we use the universal evaluation metrics, such as the AP (average precision) @ IoU (Intersection over Union)=0.5 and mIoU (mean value of IoU) to evaluate the performance of precise localization. The experiment results show that our method outperforms the existing ones for precise object localization in AMMW images, where the improvement of the AP@0.5 is about 38% and that of the mIoU is about 27%.

Concealed Object Detection for Activate Millimeter Wave Image

Active millimeter wave (AMMW) imaging technique has been widely applied in the security industries due to its under-controlled privacy concerns and no health hazards. In fact, how to automatically and precisely detect the concealed objects on the human body in the AMMW images is one key issue in industrial security scanner systems. In this paper, we first investigate the deep-learning-based object detection approaches for the AMMW images, and then, we develop a concealed object detector for the security system in the airport. For our particular application, the concealed objects include several small items such as the knife, the lighter, the phone, and so on. However, most of the current deep-learning-based methods focus mainly on detecting large objects, which occupy a large part in an image, resulting in the unsatisfactory performance on small objects. The reason lies in that the signal for the small region is rather weak before feeding into the detector. To address this issue, we first enlarge the resolution of the feature map by applying the dilated convolution. Then, we propose a context embedding object detection network in which the dilated convolutional operations with different dilations are conducted on the final feature maps. In this manner, the detector can capture both details and the context information to boost the performance of small object detection. Besides, we build a new large-scale dataset to benchmark the concealed object detection tasks in the AMMW images, which includes more than 58k AMMW images. With the proposed algorithm, we finally achieve 90.05% in detection rate and 9.73% in false alarm rate in our dataset.

Optimal Non-Invasive Fault Classification Model for Packaged Ceramic Tile Quality Monitoring Using MMW Imaging

Millimeter wave (MMW) frequency has emerged as an efficient tool for different stand-off imaging applications. In this paper, we have dealt with a novel MMW imaging application, i.e., non-invasive packaged goods quality estimation for industrial quality monitoring applications. An active MMW imaging radar operating at 60 GHz has been ingeniously designed for concealed fault estimation. Ceramic tiles covered with commonly used packaging cardboard were used as concealed targets for undercover fault classification. A comparison of computer vision-based state-of-the-art feature extraction techniques, viz, discrete Fourier transform (DFT), wavelet transform (WT), principal component analysis (PCA), gray level co-occurrence texture (GLCM), and histogram of oriented gradient (HOG) has been done with respect to their efficient and differentiable feature vector generation capability for undercover target fault classification. An extensive number of experiments were performed with different ceramic tile fault configurations, viz., vertical crack, horizontal crack, random crack, diagonal crack along with the non-faulty tiles. Further, an independent algorithm validation was done demonstrating classification accuracy: 80, 86.67, 73.33, and 93.33 % for DFT, WT, PCA, GLCM, and HOG feature-based artificial neural network (ANN) classifier models, respectively. Classification results show good capability for HOG feature extraction technique towards non-destructive quality inspection with appreciably low false alarm as compared to other techniques. Thereby, a robust and optimal image feature-based neural network classification model has been proposed for non-invasive, automatic fault monitoring for a financially and commercially competent industrial growth.