The detection of road drivable areas and lane lines is considered a fundamental component of autonomous driving systems. However, most existing approaches handle these tasks independently, and multi-task networks frequently neglect the inherent correlation between them while failing to differentiate various lane line types. In practice, the delineation of drivable regions is strongly influenced by both lane line characteristics and contextual street scenes. To address these limitations, a novel multi-task network—Real-time Road Drivable Area, Lane Line Detection, and Scene Identification Network (RLSNet)—is proposed. This network is designed to perform simultaneous segmentation of drivable areas, detection of lane lines, and classification of road scenes. Drivable area estimation is optimized through the integration of lane and scene cues, guided by traffic regulations. A Residual Network (ResNet)-based backbone is employed, enhanced with Bidirectional Fusion Attention (BFA) for feature encoding. This is followed by a decoder incorporating a Feature Aggregation Module (FAM) to enable effective semantic–spatial fusion. Lane line detection is further refined using a Bilateral Up-Sampling Decoder (BUSD), while scene understanding is enhanced via a Scene Classification Module (SCM). Extensive experiments conducted on the challenging Berkeley DeepDrive 100K(BDD100K) dataset have demonstrated that RLSNet achieves high accuracy in both drivable area and lane line detection by leveraging the mutual guidance of lane and scene information. Furthermore, the network maintains real-time inference speed at 93 frames per second (FPS), striking a practical balance between semantic fidelity and computational efficiency for real-world deployment. The implementation code has been made publicly available at: https://github.com/033186ZSY/RLSNet-master .

Analog circuit is an important component of modern electronic systems. However, the soft fault diagnosis of analog circuits is challenging due to their large parameter variability and complex internal structure. So, this paper proposes an automatic fault diagnosis method based on Multi-Scale 1D Convolutional Neural Network (MS-1D-CNN) for analog circuits. Considering that faults may disappear or weaken during the propagation process and cannot be manifested in the output signals, the fault diagnosis model is trained and constructed based on an optimum set of test points with the maximum degree of fault isolation and least test points. Furthermore, because the data at different test points and time periods have different influences on fault diagnosis, a mixed attention mechanism combining both channel and spatial attention is adopted to extract more critical information in the fault diagnosis model, achieving a more accurate soft fault diagnosis for analog circuits. Experiments are conducted on four widely used benchmark circuits. The results show that our method has higher accuracy of fault diagnosis than the existing methods, and the fault diagnosis model based on multi-test points data has higher accuracy than that solely based on the output signals for analog circuits.

The space-based surveillance radar system has a higher field of view and can overcome interference from Earth's atmosphere and terrain occlusion, which has been widely applied in high-threat near-Earth asteroid (NEA) warning and defense applications. Due to the limited power aperture product of the space-based system and the far distance between the radar and asteroid targets, the target signal is extremely weak. Prolonging the coherent accumulation time can effectively improve the radar detection capability of small asteroid targets, but the complex effects of range migration (RM) and Doppler frequency migration (DFM) will degrade the target coherent accumulation performance. To effectively solve this problem, an improved Keystone transform (KT) matched filtering banks method based on particle swarm optimization algorithm is proposed. Compared with traditional methods, the proposed method can not only ensure that the asteroid target detection performance is close to the theoretical optimum, but also reduce the system computation complexity. Simulation results verify the effectiveness of the proposed algorithm.

Spiking Neuron Network (SNN) uses spike sequence for data processing, so it has an excellent characteristic of low power consumption. However, due to the immaturity of learning algorithm, the multiplayer network training has difficulty in convergence. Utilizing the mature learning algorithm and fast training speed of the back-propagation network, this paper proposes a method to converse the Convolutional Neural Network (CNN) to the SNN. First, the adjustment strategy for CNN is introduced. Then after training, the weight parameters in the model are extracted, which is the corresponding synaptic weight in the layer of the SNN. Finally, a new threshold-setting algorithm based on feedback is proposed to solve the critical problem of the threshold setting of neurons in the SNN. We evaluate our method on the CIFAR-10 datasets released by Hinton’s team. The experimental results show that the image classification accuracy of the SNN is more than 98% of that of CNN, and the theoretical value of power consumption per second is 3.9[Formula: see text]mW.

Front vehicle detection technology is one of the hot spots in the advanced driver assistance system research field. This paper puts forward a method for front vehicles detection based on video-and-laser-information at night. First of all, video images and laser data are pre-processed with the region growing and threshold area expunction algorithm. Then, the features of front vehicles are extracted by use of a Gabor filter based on the uncertainty principle, and the distances to front vehicles are obtained through laser point cloud. Finally, front vehicles are automatically classified during identification with the improved sequential minimal optimization algorithm, which was based on the support vector machine (SVM) algorithm. According to the experiment results, the method proposed by this text is effective and it is reliable to identify vehicles in front of intelligent vehicles at night.

Pedestrian detection has become one of the hottest topics in intelligent traffic system because of its potential applications in driver assistance and automatic driving. In this study, a fast pedestrian detection and dynamic tracking method within vehicle‐to‐vehicle (V2V) cooperative environment is proposed. A dynamic tracking‐by‐detection framework for real‐time pedestrian detection is developed. First, a cascade classifiers, based on selected Haar‐like features, is trained to detect pedestrian. Then, CamShift algorithm combined with extended Kalman filtering is used to pedestrian dynamic tracking. Finally, with the crowdsourcing detected information, a smartphone‐based V2V cooperative warning system is developed to share useful detection results within blind spots. The experiment results show that the proposed method has a real‐time and accurate performance, which can provide a reference for road traffic safety monitoring technology.

Cycling is a typical green traffic mode, and takes a growing part of urban traffic volume. Yet limited cyclist behavior models shed light on cases at unsignalized intersections with heterogeneous traffic, where bicycle behavior is characterized by frequent confrontations with other road users (vehicles, bicycles, and pedestrians). This study developed a microscopic simulation model for cyclist behavior analysis at unsignalized intersection with heterogeneous traffic. The cyclist crossing model applied fuzzy logic and social force theory for this purpose. The parameters are either estimated directly based on empirical data or derived indirectly through maximum likelihood estimation. Finally model performance was confirmed through comparisons between estimations and observations on individual trajectory, minimum distances, and average riding speeds of collision avoidance behaviors with different conflicting road users. Simulation results indicated that the model can represent cyclist crossing behavior at unsignalized intersection with heterogeneous traffic as in the real world.