In recent years, frequent forest fires have plagued countries all over the world, causing serious economic damage and human casualties. Faster and more accurate detection of forest fires and timely interventions have become a research priority. With the advancement in deep learning, fully convolutional network architectures have achieved excellent results in the field of image segmentation. More researchers adopt these models to segment flames for fire monitoring, but most of the works are aimed at fires in buildings and industrial scenarios. However, there are few studies on the application of various fully convolutional models to forest fire scenarios, and comparative experiments are inadequate. In view of the above problems, on the basis of constructing the dataset with remote-sensing images of forest fires captured by unmanned aerial vehicles (UAVs) and the targeted optimization of the data enhancement process, four classical semantic segmentation models and two backbone networks are selected for modeling and testing analysis. By comparing inference results and the evaluation indicators of models such as mPA and mIoU, we can find out the models that are more suitable for forest fire segmentation scenarios. The results show that the U-Net model with Resnet50 as a backbone network has the highest segmentation accuracy of forest fires with the best comprehensive performance, and is more suitable for scenarios with high-accuracy requirements; the DeepLabV3+ model with Resnet50 is slightly less accurate than U-Net, but it can still ensure a satisfying segmentation performance with a faster running speed, which is suitable for scenarios with high real-time requirements. In contrast, FCN and PSPNet have poorer segmentation performance and, hence, are not suitable for forest fire detection scenarios.
The operational and safety performance of intersections is the key to ensuring the efficient operation of urban traffic. With the development of automated driving technologies, the ability of adaptive traffic signal control has been improved according to data detected by connected and automated vehicles (CAVs). In this paper, an adaptive traffic signal control was proposed to optimize the operational and safety performance of the intersection. The proposed algorithm based on Q-learning considers the data detected by loop detectors and CAVs. Furthermore, a comprehensive analysis was conducted to verify the performance of the proposed algorithm. The results show that the average delay and conflict rate have been significantly optimized compared with fixed timing and traffic actuated control. In addition, the performance of the proposed algorithm is good in the test of the irregular intersection. The algorithm provides a new idea for the intelligent management of isolated intersections under the condition of mixed traffic flow. It provides a research basis for the collaborative control of multiple intersections.
Phase unwrapping method based on Residual Auto Encoder Network is proposed in this chapter. Phase unwrapping is regarded as a multiple classification problem, and it will be solved by the trained network model. Through training and validation stages, optimal network models can be served as predictors of wrap count distribution map of wrapped phase. Then merge the wrapped phase and count together to complete unwrapping. Software simulation and hardware acquisition are the sources of training dataset. To further improve accuracy of unwrapping, image analysis-based optimization method is designed that can remove misclassification and noise points in initial result. In addition, phase data stitching by Iterative Closest Point is adopted to realize dynamic resolution and enhance the flexibility of method. Point diffraction interferometer and multi-step phase extraction technique is the foundation of proposed method. It can be concluded from experiments that the proposed method is superior to state-of-art ones in accuracy, time efficiency, anti-noise ability, and flexibility. Request access from your librarian to read this chapter's full text.