Public safety and intelligent surveillance systems rely on anomaly detection for effective monitoring. In real-world pedestrian detection scenarios, Pedestrians often exhibit various symmetrical features such as body contours, facial features, posture, and clothing. However, the accuracy of pedestrian anomaly detection is affected by factors such as complex backgrounds, pedestrian obstruction, and small target sizes. To address these issues, this study introduced YOLO-ABD, a lightweight method for anomaly behavior detection that integrated small object detection and channel shuffling. This approach enhanced the YOLOv8n baseline model by integrating a small-object detection mechanism at the head and employing the symmetric GSConv convolutional module in the backbone network to improve perceptual capabilities. Furthermore, it incorporated the SimAM attention mechanism to mitigate complex background interference and thus enhance target detection performance. Evaluation on the IITB-Corridor dataset showed mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further underscored the superiority of YOLO-ABD over advanced detection algorithms, demonstrating its effectiveness and generalization capabilities. With relatively fewer parameters, YOLO-ABD provided an excellent lightweight solution for pedestrian anomaly detection.

Tomographic Gamma Scanning (TGS) is one of the most important non-destructive analyzed techniques for radioactive waste drums. By reconstructing the radioactivity distribution image, it can accurately realize the qualitative, quantitative, and positioning analysis of the radionuclides in the drum. However, the time consuming of the scanning is long and the reconstructed image is rough, which limits its good application in the practical assay of the waste drum. In this work, the total variational minimization (TVM) method was applied to improve the iterative process of the conventional algorithms of maximum likelihood expectation maximization (MLEM) and algebraic reconstruction technique (ART), then the MLEM-TVM and ART-TVM reconstruction methods were developed. The transmitted experiments were carried out where four kinds of materials were arranged in a segment whose densities ranging from 1.04 g/cm ³ to 2.02 g/cm ³ and a ¹⁵² Eu isotope was set up as a transmission source. Compared with the traditional algorithms MLEM and ART, the MLEM-TVM and the ART-TVM algorithms have a better performance on the accuracy and the signal-to-noise ratio, and the MLEM-TVM algorithm achieves the best results, which means the quality of the reconstructed image is improved. The accuracy and effectiveness of the TVM method used in the TGS image reconstruction are verified in the work, and moreover, it can save the scanning time and enhance the TGS image resolution through sparse projection sampling.

Tomographic gamma scanning (TGS) is a nondestructive testing (NDT) method commonly used for radioactive waste. Traditional transmission image reconstruction algorithm require the projection data to match the line integral value of the reconstructed image in the corresponding projection direction, and use a single detector for scanning, resulting in cumbersome and time-consuming scanning processes that severely limit the industrial application of TGS. Sparse angular scanning can effectively improve the efficiency of TGS systems. However, the amount of data generated by sparse angular scanning can make it difficult to support traditional algorithms, resulting in blurry artifacts in the reconstructed image. This work utilizes array detectors to achieve fast and high-precision reconstruction for TGS transmission images under sparse angular scanning, based on the Algebraic Reconstruction Technique (ART) and a new residual network (ResNeXt). Geant4 simulation and a self-developed TGS device with array detectors were used for both simulation experiments and real experiments to verify the proposed method. The proposed method was compared to other algorithms, including ART, ART-NLM, ART-TV, and ART-DenseNet, using two metrics, MSE and SSIM, for evaluation. The experimental results show that the average MSE of ResNeXt is 56.3%, 26.5%, 24.4%, and 8.4% lower than ART, ART-NLM, ART-TV, and DenseNet, respectively. The SSIM averages are 36.4%, 14.8%, 15.3%, and 4.8% higher than ART, ART-NLM, ART-TV, and DenseNet, respectively. It can be concluded that when using the same sparse projection data, the improved ART-ResNeXt reconstruction methods generate TGS transmission images with better reconstruction quality and faster reconstruction speed compared to reconstruction methods like ART, ART-NLM, ART-TV and ART-DenseNet. The improved ResNeXt exhibits significant adaptability. Even when encountering gamma ray energy and medium types that are not present in the neural network training set, the reconstruction process achieves the highest quality while maintaining the fastest speed possible.