Guoxin Zhang

With the development of the computers, people's demand for image processing technology is increasing day by day, and many new algorithms have been created, further promoting the development of the field of image processing. Among them, morphological processing of color images plays an important role. In this research study, it is proposed the novel perspectives on the morphology extraction and analysis of calligraphy fonts images. In the classical morphological image processing, the structured information reflected by the pixel values in the image is not considered, to deal with this, the proposed model has 3 focuses: (1) image invariant moments as initial processing is used to serve as the basic step of processing the information. The Krawtchouk moment and Tchebichef orthogonal scale polynomial model are combined to make the algorithm efficient; (2) color morphology extraction and analysis of images is conducted as well as keeping the structural information; (3) novel neural network model is proposed to extract the features. Through the experiment, it can be seen that the proposed model can effectively obtain the image features.

This paper presents a lane departure detection approach that utilizes a stacked sparse autoencoder (SSAE) for vehicles driving on motorways or similar roads. Image preprocessing techniques are successfully executed in the initialization procedure to obtain robust region-of-interest extraction parts. Lane detection operations based on Hough transform with a polar angle constraint and a matching algorithm are then implemented for two-lane boundary extraction. The slopes and intercepts of lines are obtained by converting the two lanes from polar to Cartesian space. Lateral offsets are also computed as an important step of feature extraction in the image pixel coordinate without any intrinsic or extrinsic camera parameter. Subsequently, a softmax classifier is designed with the proposed SSAE. The slopes and intercepts of lines and lateral offsets are the feature inputs. A greedy, layer-wise method is employed based on the inputs to pretrain the weights of the entire deep network. Fine-tuning is conducted to determine the global optimal parameters by simultaneously altering all layer parameters. The outputs are three detection labels. Experimental results indicate that the proposed approach can detect lane departure robustly with a high detection rate. The efficiency of the proposed method is demonstrated on several real images.

The traditional adaptive cruise control system generally requires 25–40 km/h velocity to function. Moreover, the adaptive cruise control system cannot decelerate to the stop state, cannot adjust for stationary objects, and has limited scope of application. This study achieved the traffic jam tracking function of vehicles through the simultaneous use of millimeter wave and laser sensors and the analysis of the driving behavior of skilled drivers. The spacing and acceleration control of a vehicle is optimized based on the premise of ensuring safety and comfort by providing smooth, comfortable, safe, and radical control modes for driver selection, thereby increasing the probability that adaptive cruise control adopted by drivers. In addition, the collision avoidance function is added for safety reasons. Finally, actual vehicle experiments show that the distance and acceleration errors are in the expected range of errors of drivers. Moreover, the validity and practicability of the proposed adaptive cruise control algorithm are verified.

Manual calibration and testing on real vehicles are common methods of generating shifting schedules for newly developed vehicles. However, these methods are time-consuming. Shifting gear timing is an important operating parameter that affects shifting time, power loss, fuel efficiency, and driver comfort. The stacked autoencoder (SAE) algorithm, a type of artificial neural network, is used in this study to predict shifting gear timing on the basis of throttle percentage, vehicle velocity, and acceleration. Experiments are conducted to obtain training and testing data. Different neural networks are trained with experimental data on a real vehicle under different road conditions collected using the CANcaseXL device and control AMESim simulation model, which was constructed based on real vehicle parameters. The input number of SAE is determined through a comparison between two and three parameters. The output type of SAE is determined through a comparative experiment on pattern recognition and multifitting. Meanwhile, the network structure of SAE is determined through a comparative experiment on simple and deep-learning neural networks. Experimental results demonstrate that using the SAE intelligent shift control strategy to determine shift timing not only is feasible and accurate but also saves time and development costs.

This study employs the mechanical vibration and acoustic waves of a hydraulic support tail beam for an accurate and fast coal-rock recognition. The study proposes a diagnosis method based on bimodal deep learning and Hilbert-Huang transform. The bimodal deep neural networks (DNN) adopt bimodal learning and transfer learning. The bimodal learning method attempts to learn joint representation by considering acceleration and sound pressure modalities, which both contribute to coal-rock recognition. The transfer learning method solves the problem regarding DNN, in which a large number of labeled training samples are necessary to optimize the parameters while the labeled training sample is limited. A suitable installation location for sensors is determined in recognizing coal-rock. The extraction features of acceleration and sound pressure signals are combined and effective combination features are selected. Bimodal DNN consists of two deep belief networks (DBN), each DBN model is trained with related samples, and the parameters of the pretrained DBNs are transferred to the final recognition model. Then the parameters of the proposed model are continuously optimized by pretraining and fine-tuning. Finally, the comparison of experimental results demonstrates the superiority of the proposed method in terms of recognition accuracy.