No abstract

Due to the flammability, explosiveness and toxicity of continuous objects (e.g., chemical gas, oil spill, radioactive waste) in the petrochemical and nuclear industries, boundary tracking of continuous objects is a critical issue for industrial wireless sensor networks (IWSNs). In this article, we propose a continuous object boundary tracking algorithm for IWSNs-which fully exploits the collective intelligence and machine learning capability within the sensor nodes. The proposed algorithm first determines an upper bound of the event region covered by the continuous objects. A binary tree-based partition is performed within the event region, obtaining a coarse-grained boundary area mapping. To study the irregularity of continuous objects in detail, the boundary tracking problem is then transformed into a binary classification problem; a hierarchical soft margin support vector machine training strategy is designed to address the binary classification problem in a distributed fashion. Simulation results demonstrate that the proposed algorithm shows a reduction in the number of nodes required for boundary tracking by at least 50%. Without additional fault-tolerant mechanisms, the proposed algorithm is inherently robust to false sensor readings, even for high ratios of faulty nodes (≈ 9%).

Object detection is an important part of autonomous driving technology. To ensure the safe running of vehicles at high speed, real-time and accurate detection of all the objects on the road is required. How to balance the speed and accuracy of detection is a hot research topic in recent years. This paper puts forward a one-stage object detection algorithm based on YOLOv4, which improves the detection accuracy and supports real-time operation. The backbone of the algorithm doubles the stacking times of the last residual block of CSPDarkNet53. The neck of the algorithm replaces the SPP with the RFB structure, improves the PAN structure of the feature fusion module, adds the attention mechanism CBAM and CA structure to the backbone and neck structure, and finally reduces the overall width of the network to the original 3/4, so as to reduce the model parameters and improve the inference speed. Compared with YOLOv4, the algorithm in this paper improves the average accuracy on KITTI dataset by 2.06% and BDD dataset by 2.95%. When the detection accuracy is almost unchanged, the inference speed of this algorithm is increased by 9.14%, and it can detect in real time at a speed of more than 58.47 FPS.

No abstract

Geological interpretation based on gravity gradiometry data constitutes a very challenging problem. Rigorous 3D inversion is the main technique used in quantitative interpretation of the gravity gradiometry data. An alternative approach to the quantitative analysis of the gravity gradiometry data is based on 3D smooth potential field migration. This rapid imaging approach, however, has the shortcomings of providing smooth images since it is based on direct integral transformation of the observed gravity tensor data. Another limitation of migration transformation is related to the fact that, in a general case, the gravity data generated by the migration image do not fit the observed data well. In this paper, we describe a new approach to rapid imaging that allows us to produce the density distribution which adequately describes the observed data and, at the same time, images the structures with anomalous densities having sharp boundaries. This approach is based on the basic theory of potential field migration with a focusing stabilizer in the framework of regularized scheme, which iteratively transfers the observed gravity tensor field into an image of the density distribution in the subsurface formations. The results of gravity migration can also be considered as an a priori model for conventional inversion subsequently. We demonstrate the practical application of migration imaging using both synthetic and real gravity gradiometry data sets acquired for the Nordkapp Basin in the Barents Sea.

No abstract

As a crucial component of the autonomous driving task, the vehicle target detection algorithm directly impacts driving safety, particularly in inclement weather situations, where the detection precision and speed are significantly decreased. This paper investigated the You Only Look Once (YOLO) algorithm and proposed an enhanced YOLOv4 for real-time target detection in inclement weather conditions. The algorithm uses the Anchor-free approach to tackle the problem of YOLO preset anchor frame and poor fit. It better adapts to the detected target size, making it suitable for multi-scale target identification. The improved FPN network transmits feature maps to unanchored frames to expand the model's sensory field and maximize the utilization of model feature data. Decoupled head detecting head to increase the precision of target category and location prediction. The experimental dataset BDD-IW was created by extracting specific labeled photos from the BDD100K dataset and fogging some of them to test the proposed method's practical implications in terms of detection precision and speed in Inclement weather conditions. The proposed method is compared to advanced target detection algorithms in this dataset. Experimental results indicated that the proposed method achieved a mean average precision of 60.3%, which is 5.8 percentage points higher than the original YOLOv4; the inference speed of the algorithm is enhanced by 4.5 fps compared to the original, reaching a real-time detection speed of 69.44 fps. The robustness test results indicated that the proposed model has considerably improved the capacity to recognize targets in inclement weather conditions and has achieved high precision in real-time detection.

No abstract