The continuous mutation of the novel coronavirus necessitates effective urban public health safety measures. In public spaces, enforcing social distancing is crucial to prevent droplet transmission of the virus. Existing video detection methods are limited by blind spots, especially in densely populated areas. This paper introduces an innovative millimeter wave radar method for effective social distancing control. Unlike traditional radar technology, our approach employs energy accumulation and Doppler compensation techniques to reduce preprocessing interference notably and accurately differentiate between human and non-human entities. We have fine-tuned the sensor configuration through distance feedback, thereby enhancing detection resolution. Multiple micro-Doppler images at various spatial scales are acquired and concatenated to construct a three-dimensional data cube. This serves as input to our network model to achieve higher detection accuracy. Our experiments demonstrate that this method surpasses mainstream video and radar detection solutions, offering broader coverage, increased stability, and the ability to discern distances to humans with a resolution as acceptable as 10 centimeters.
The mainstream methods for change detection in synthetic-aperture radar (SAR) images use difference images to define the initial change regions. However, methods can suffer from semantic collapse, which makes it difficult to determine semantic information about the changes. In this paper, we proposed a hierarchical fusion SAR image change-detection model based on hierarchical fusion conditional random field (HF-CRF). This model introduces multimodal difference images and constructs the fusion energy potential function using dynamic convolutional neural networks and sliding window entropy information. By using an iterative convergence process, the proposed method was able to accurately detect the change-detection regions. We designed a dynamic region convolutional semantic segmentation network with a two-branch structure (D-DRUNet) to accomplish feature fusion and the segmentation of multimodal difference images. The proposed network adopts a dual encoder–single decoder structure where the baseline is the UNet network that utilizes dynamic convolution kernels. D-DRUNet extracts multimodal difference features and completes semantic-level fusion. The Sobel operator is introduced to strengthen the multimodal difference-image boundary information and construct the dynamic fusion pairwise potential function, based on local boundary entropy. Finally, the final change result is stabilized by iterative convergence of the CRF energy potential function. Experimental results demonstrate that the proposed method outperforms existing methods in terms of the overall number of detection errors, and reduces the occurrence of false positives.
Target detection and tracking algorithms are one of the key technologies in the field of autonomous driving in intelligent transportation, providing important sensing capabilities for vehicle localization and path planning. Siamese network-based trackers formulate the visual tracking mission as an image-matching process by regression and classification branches, which simplifies the network structure and improves the tracking accuracy. However, there remain many problems, as described below. (1) The lightweight neural networks decrease the feature representation ability. It is easy for the tracker to fail under the disturbing distractors (e.g., deformation and similar objects) or large changes in the viewing angle. (2) The tracker cannot adapt to variations of the object. (3) The tracker cannot reposition the object that has failed to track. To address these issues, we first propose a novel match filter arbiter based on the Euclidean distance histogram between the centers of multiple candidate objects to automatically determine whether the tracker fails. Secondly, the Hopcroft–Karp algorithm is introduced to select the winners from the dynamic template set through the backtracking process, and object relocation is achieved by comparing the Gradient Magnitude Similarity Deviation between the template and the winners. The experiments show that our method obtains better performance on several tracking benchmarks, i.e., OTB100, VOT2018, GOT-10k, and LaSOT, compared with state-of-the-art methods.
Image segmentation is a process that densely classifies image pixels into different regions corresponding to real world objects. However, this correspondence is not always exact in images since there are many uncertainty factors, e.g., recognition hesitation, imaging equipment, condition, and atmosphere environment. To achieve the segmentation result with low uncertainty and reduce the influence on the subsequent procedures, e.g., image parsing and image understanding, we propose a novel stochastic active contour model based on intuitionistic fuzzy set, in which the hesitation degree is leveraged to model the recognition uncertainty in image segmentation. The advantages of our model are as follows. (1) Supported by fuzzy partition, our model is robust against image noise and inhomogeneity. (2) Benefiting from the stochastic process, our model easily crosses saddle points of energy functional. (3) Our model realizes image segmentation with low uncertainty and co-produces the quantitative uncertainty degree to the segmentation results, which is helpful to improve reliability of intelligent image systems. The associated experiments suggested that our model could obtain competitive segmentation results compared to the relevant state-of-the-art active contour models and could provide segmentation with a pixel-wise uncertainty degree.
14 December 2023 in IEEE Transactions on Network Science and Engineering
Semantic segmentation of large-scale point clouds is a research hotspot in aerospace remote sensing technology. Large-scale point clouds face the curse of dimensionality, and there are two problems to resolve, i.e., severe feature loss caused by down-sampling and tricky balance between segmentation performance and computational cost. In this paper, we propose the FAR-Net, a novel point cloud segmentation method based on feature aggregation-recoding, to infer point-level semantics of large-scale point clouds at reasonable cost. This network has three major features. First, local difference attention coding preserves feature details. Second, a hierarchical feature aggregation module based on keypoints and voxels is designed with two branches. The keypoint branch uses k-means clustering to generate keypoints that are globally associated by Point Transformer. The voxel branch adopts a multi-scale structure with three cascaded 3D CNN modules to extract local spatial features. Third, a binary feature recoding module divides intra-cluster point clouds into two categories by a binary classifier, and assigns keypoint features and difference features according to the binary label to increase feature differences. Experiments show that our network achieves competitive segmentation performance on both indoor and outdoor large-scale 3D point cloud datasets.