Fully convolutional networks (FCNs) have shown outstanding performance in image semantic segmentation, which is the key work in license plate detection (LPD). An FCN architecture for LPD is presented. First, a multiscale hierarchical network structure is used to combine multiscale and multilevel features produced by FCN. Then, an enhanced loss structure that contains three loss layers is defined to emphasize the license plates in images. Finally, the FCN generates prediction maps that directly show the location of license plates. Experiments show that our approach is more accurate than many state-of-the-art methods.

With the rapid development of smart cities, vehicle detection algorithms have become a crucial component of intelligent transportation systems, widely applied in areas such as parking detection, traffic flow analysis, and illegal intrusion detection. However, due to limitations in computational resources and the increasing complexity of traffic scenarios, vehicle detection algorithms face considerable performance requirements and a demand for lightweight models. Therefore, we propose a lightweight vehicle detection model that incorporates a parallel multi-scale aggregation (PMSA) module into an improved You Only Look Once (YOLO) v5 architecture, termed PMSA-YOLO. First, the backbone network is optimized by designing a PMSA, which not only captures multi-scale information but also reduces reliance on network depth and width while maintaining recognition efficiency. Second, a convolutional block attention module is added to the last layer of the backbone network to enhance the extraction of key features, thereby improving feature recognition efficiency. Finally, a bidirectional feature pyramid network module is integrated into the neck network, and a more streamlined PMSA module is adopted for feature fusion. Experimental results demonstrate that relative to the original model, the improved model reduces the parameter count and computational load by 29.7% and 32.9%, respectively, while increasing precision, recall, mAP50, and mAP50–95 by 4.5%, 3.4%, 4.4%, and 2.6%, respectively.

Privacy-Preserving Computational Geometry is a kind of special secure multi-party computation problem. As a special privacy-preserving computational geometry problem, Privacy- Path Determination may be applied in many fields such as military field and commerce field. In this paper, a privacy-preserving line-ellipse position relation determination protocol is developed and based on this protocol, a private-preserving segment-ellipse intersect-determination protocol is presented, and their correctness, security and complexity are analyzed.

A (1,0)-super solution is a satisfying assignment such that if the value of any one variable is flipped to the opposite value, the new assignment is still a satisfying assignment. Namely, every clause must contain at least two satisfied literals. Because of its robustness, super solutions are concerned in combinatorial optimization problems and decision problems. In this paper, we investigate the existence conditions of the (1,0)-super solution of $(k,s)$ -CNF formula, and give a reduction method that transform from k-SAT to (1,0)- $(k+1,s)$ -SAT if there is a ( $k+1,s$ )-CNF formula without a (1,0)-super solution. Here, $(k,s)$ -CNF is a subclass of CNF in which each clause has exactly k distinct literals, and each variable occurs at most s times. (1,0)- $(k,s)$ -SAT is a problem to decide whether a $(k,s)$ -CNF formula has a (1,0)-super solution. We prove that for $k>3$ , if there exists a $(k,s)$ -CNF formula without a (1,0)-super solution, (1,0)- $(k,s)$ -SAT is NP-complete. We show that for $k>3$ , there is a critical function $\phi \left(k\right)$ such that every $(k,s)$ -CNF formula has a (1,0)-super solution for $s\le \phi \left(k\right)$ and (1,0)- $(k,s)$ -SAT is NP-complete for $s>\phi \left(k\right)$ . We further show some properties of the critical function $\phi \left(k\right)$ .

The effective use of context information can significantly improve the effect of object detection. This paper proposes a method to exploit the context of a hard example searched by online hard example mining for improving the detection effect for people in crowded scenes. As shown by these experiments, this method can improve the effectiveness of faster R-CNN networks on people detection with a smaller convolutional neural network model. Because smaller convolutional neural network model is used, both the running memory consumption and the computing time can be reduced. Hence, our method can be implemented more easily on embedded devices.