Search

Automatic lane change of vehicles requires driving at the fastest possible speed while ensuring no collision situations. However, regular control is not robust enough to handle unexpected situations or respond to lane separation. To solve these problems, an automatic lane change decision model based on dueling double deep Q-network(D3QN) reinforcement learning model is proposed. The algorithm processes the environmental vehicle information fed back by the internet of vehicles, and then obtains actions through strategies. After the actions are executed, the neural network is trained according to given reward function, and finally the automatic lane change strategy is realized through the trained network and reinforcement learning. The three-lane environment built by Python and the vehicle simulation software CarMaker are used to carry out simulation experiments. The results show that the algorithm proposed has a good control effect, making it feasible and effective. [ABSTRACT FROM AUTHOR]

A conditional generative adversarial network-based high perceptual image compression(HPIC) model was proposed to obtain a compressed image that conforms to human visual perception. In HPIC， the original image was encoded and quantized based on a hyper prior probability model. A generator based on the conditional additional label and residual module was used for the reconstruction of the compressed image， and a discriminator based on the convolutional neural network was used to distinguish the difference between the compressed image and the real image. Based on the bit rate-distortion-perception optimization theory to design the loss function， the perceptual distortion metric was chosen based on the eigenvalues of the pre-trained inception network to achieve image compression reconstruction with high perceptual quality on the one hand， and use the adversarial generation network loss to eliminate compression artifacts and improve the compression accuracy on the other hand. The experimental results show that HPIC achieves a good balance in the bit rate-distortion-perception tradeoff and outperforms the current common algorithms in all perceptual metrics scores， even though the latter uses twice as much bit rate as ours. HPIC can achieve compression with high perceptual quality. [ABSTRACT FROM AUTHOR]

Aiming at multi-focus image fusion, the complementary information at each scale is fused in a targeted manner using a multi-scale fusion method. First, the source image is decomposed into a background layer and a detail layer using the L0 gradient minimization smoothing method, and then a fractional-order edge detection mask is used to preserve the edge information in the background layer, and a fractional-order gradient energy operator is introduced in the detail layer for weight assignment. The experimental results show that the proposed fractional-order gradient energy operator is more sensitive than the integer-order gradient energy clarity operator, which is consistent with the human visual perception. The fusion method proposed effectively avoids artifacts and block effects in the fused images, and retains the source image information more fully. [ABSTRACT FROM AUTHOR]

The admissibility issue of discrete singular systems was mainly studied. Applying restricted equivalent transformations of the discrete singular system， a new necessary and sufficient condition was proposed to ensure discrete singular system admissible. By introducing an intermediate matrix to configure partial poles of system matrix such that the closed-loop system is regular， a state feedback controller was designed to make the closed-loop system admissible. Using similar methods， the controller design problem of uncertain discrete singular systems was discussed as well， a sufficient condition of robust stabilization for uncertain discrete singular systems was obtained. All the methods proposed in this article are strictly linear matrix inequalities(LMI). Two numerical examples verify the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Ｉｎ ｏｒｄｅｒ ｔｏ ａｖｏｉｄ ｔｈｅ ｂｌｕｒｒｉｎｇ ｏｆ ｉｍａｇｅ ｂｙ ｃｌａｓｓｉｃａｌ ｍｅｄｉａｎ ｆｉｌｔｅｒ, ａ ｎｏｉｓｅ ｄｅｔｅｃｔｉｏｎ ｍｏｄｅｌ ｗａｓ ｅｓｔａｂｌｉｓｈｅｄ. Ａ ｓｗｉｔｃｈｉｎｇ ｆｉｌｔｅｒ ｗａｓ ｄｅｓｉｇｎｅｄ ｂｙ ｄｅｔｅｃｔｉｎｇ ｎｏｉｓｅ. Ｗｈｅｎ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ｐｏｉｎｔ ｉｓ ｎｏｉｓｙ, ｔｈｅ ｍｅｄｉａｎ ｆｉｌｔｅｒ ｗａｓ ｕｓｅｄ ｆｏｒ ｄｅｎｏｉｓｉｎｇ. Ｗｈｅｎ ｔｈｅ ｄｅｔｅｃｔｉｏｎ ｐｏｉｎｔ ｉｓ ｎｏｎ-ｎｏｉｓｙ ｐｏｉｎｔ, ｔｈｅ ｆｒａｃｔｉｏｎａｌ ｄｉｆｆｅｒｅｎｔｉａｌ ｆｉｌｔｅｒ ｗａｓ ｕｓｅｄ ｔｏ ｅｎｈａｎｃｅ ｔｈｅ ｉｍａｇｅ. Ｔｈｅ ｐｒｏｐｏｓｅｄ ａｌｇｏｒｉｔｈｍ ｃａｎ ｎｏｔ ｏｎｌｙ ｅｆｆｅｃｔｉｖｅｌｙ ｒｅｍｏｖｅ ｔｈｅ ｓａｌｔ ａｎｄ ｐｅｐｐｅｒ ｎｏｉｓｅ ｉｎ ｔｈｅ ｉｍａｇｅ, ｂｕｔ ａｌｓｏ ｅｎｈａｎｃｅ ｔｈｅ ｉｍａｇｅ, ｓｏ ｔｈａｔ ｔｈｅ ｉｍａｇｅ ｒｅｔａｉｎｓ ｔｈｅ ｄｅｔａｉｌｓ ｉｎｔａｃｔ ｗｈｅｎ ｔｈｅ ｅｄｇｅ ｉｓ ｐｒｏｔｒｕｄｉｎｇ. Ｓｅｌｅｃｔｉｎｇ “Ｌｅｎａ” ａｎｄ ｏｔｈｅｒ ｃｌａｓｓｉｃ ｉｍａｇｅｓ ｆｏｒ ｍｕｌｔｉｐｌｅ ｅｘｐｅｒｉｍｅｎｔｓ ａｎｄ ａｎａｌｙｓｉｓ, ｔｈｅ ｒｅｓｕｌｔｓ ｓｈｏｗｅｄ ｔｈｅ ｅｆｆｅｃｔｉｖｅｎｅｓｓ ｏｆ ｔｈｅ ｐｒｏｐｏｓｅｄ ａｌｇｏｒｉｔｈｍ ｉｎ ｉｍａｇｅ ｄｅｎｏｉｓｉｎｇ ａｎｄ ｅｎｈａｎｃｅｍｅｎｔ. [ABSTRACT FROM AUTHOR]

The observer for the uncertain fractional-order system with sensor fault and system measurement noise is developed. By using the method of augmented matrix and the invariant property of matrix rank， the uncertain fractional-order system is augmented into the singular fractional-order uncertain system. Based on the linear matrix inequality approach of stability criterion for fractional-order systems， an asymptotic stability criterion of the error dynamic system with fractional-order satisfying 1 [ABSTRACT FROM AUTHOR]