Lane detection is critical for intelligent vehicles to sense drivable areas. Compared to general objects, lane lines are slender-shaped, easily occluded, or defaced. Therefore, the lane detection network requires a more robust ability for local detail extraction and global semantic information modeling. In this paper, we propose a novel lane detection network (FLAMNet) with a flexible line anchor mechanism, which constantly corrects the position of line anchors to improve detection performance and computational efficiency. Specifically, we utilize the Patch Pooling Aggregation Module (PPAM) to aggregate multi-scale semantic features extracted by the backbone network. The multi-scale features are subsequently inputted into DSAformer, which utilizes decomposed self-attention to establish global long-distance dependencies. The detection head leverages fused features of multi-scale global and local details to accurately fit the lane line by correcting the anchor position. Moreover, we propose the Horizontal Information Aggregation Module (HIAM) to expand the receptive field of line anchors horizontally, enhancing the line anchor representation ability to the topological structure of complex lane lines. The experimental results on mainstream lane detection benchmark datasets demonstrate that the proposed FLAMNet outperforms existing methods. We have uploaded the code and demo of FLAMNet on GitHub at: https://github.com/ RanHao-cq/FLAMNet.

Due to various reasons, such as limitations in data collection and interruptions in network transmission, gathered data often contain missing values. Existing state-of-the-art generative adversarial imputation methods face three main issues: limited applicability, neglect of latent categorical information that could reflect relationships among samples, and an inability to balance local and global information. We propose a novel generative adversarial model named DTAE-CGAN that incorporates detracking autoencoding and conditional labels to address these issues. This enhances the network’s ability to learn inter-sample correlations and makes full use of all data information in incomplete datasets, rather than learning random noise. We conducted experiments on six real datasets of varying sizes, comparing our method with four classic imputation baselines. The results demonstrate that our proposed model consistently exhibited superior imputation accuracy.

The research of data mining has aroused widespread concern in academia and industry. However, an important mark of the Internet of Things era is that sensor data replaces artificially compiled data. How to extract valuable knowledge and patterns from a large amount of data generated by sensors is a meaningful research topic. This paper proposes a dynamic data mining framework for processing sensor data. A sensor data mining model which can be used in the process of dynamic change is constructed. In this model, different sensor network environments are considered as different physical systems. The physical system and its parameters are trained by collecting and mining historical changes in sensor data; the associations between different sensor network environments are discovered by mining the associations between the parameters of different physical systems. In our limited experimental environment, the physical quantities considered included transmission distance, transmission delay, sensor data, data changes, and so on. Experiments were carried out on the designated experimental platform, and the results showed that the model could mine the dynamic data and find stable patterns. Through the analysis of the experimental results, it was found that the model had reference value for the dynamic mining of sensor data, and was expected to construct new methods for industrial big data analysis.