The object detection networks with high accuracy are hard to be directly deployed on end-devices such as vehicles and drones due to their significant increase of parameters and computational cost. In order to solve the problem, by considering network compression and computation acceleration, a new compression scheme for residual networks was proposed to compress YOLOv3 (You Only Look Once v3), and this compressed network was then accelerated on ZYNQ platform. Firstly, a network compression algorithm containing both network pruning and network quantization was proposed. In the aspect of network pruning, a strategy for residual structure was introduced to divide the network pruning into two granularities:channel pruning and residual connection pruning, which overcame the limitations of the channel pruning on residual connections and further reduced the parameter number of the model. In the aspect of network quantization, a relative entropy-based simulated quantization was utilized to quantize the parameters channel by channel, and perform the online statistics of the parameter distribution and the information loss caused by the parameter quantization, so as to assist to choose the best quantization strategy to reduce the precision loss during the quantization process. Secondly, the 8-bit convolution acceleration module was designed and optimized on ZYNQ platform, which optimized the on-chip cache structure and accelerate the compressed YOLOv3 with combining the Winograd algorithm. Experimental results show that the proposed solution can achieve smaller model scale and higher accuracy (7 percent points increased) compared to YOLOv3 tiny. Meanwhile, the hardware acceleration method on ZYNQ platform achieves higher energy efficiency ratio than other platforms, thus helping the actual deployment of YOLOv3 and other residual networks on the end sides of ZYNQ.

In order to solve the problems such as slow convergence speed, falling into local optimum easily, unsmooth planning path and high cost of traditional genetic algorithm, an Unmanned Aerial Vehicle (UAV) path planning method based on improved Genetic Algorithm (GA) was proposed. The selection operator, crossover operator and mutation operator of genetic algorithm were improved to planning a smooth and effective flight path. Firstly, an environment model suitable for the field information acquisition of UAV was established, and a more complex and accurate mathematical model suitable for this scene was established by considering the objective function and constraints of UAV. Secondly, the hybrid non-multi-string selection operator, asymmetric mapping crossover operator and heuristic multi-mutation operator were proposed to find the optimal path and expand the search range of the population. Finally, a cubic B-spline curve was used to smooth the planned path to obtain a smooth flight path and reduce the calculation time of the algorithm. Experimental results show that, compared with the traditional GA, the cost value of the proposed algorithm was reduced by 68%, and the number of convergence iterations was reduced by 67%; compared with the Ant Colony Optimization (ACO) algorithm, its cost value was reduced by 55% and the number of convergence iterations was reduced by 58%. Through a large number of comparison experiments, it is concluded that when the value of the crossover rate is the reciprocal of chromosome size, the proposed algorithm has the best convergence effect. After testing the algorithm performance in different environments, it can be seen that the proposed algorithm has good environmental adaptability and is suitable for path planning in complex environments.

Considering the false alarm and miss detection during testing and diagnosis of complex system, a new method was proposed to solve test selection problems under unreliable test based on Simulated Annealing Particle Swarm Optimization (SA-PSO) algorithm. Firstly, a heuristic function was established to evaluate the capability of test point detection, coverage and reliance. Then, combining the heuristic function with the least test cost principle and considering the requirement of testability targets, a fitness function to ensure optimal selection was designed. Lastly, the process and key steps of SA-PSO were introduced and the superiority of this algorithm was verified by simulation results of launch system of Apollo. The results show that the proposed method can find the global optimal test points. It can minimize test cost on requirement of testability targets and has higher fault detection and isolation rate compared with greedy algorithm and genetic algorithm.

Concerning the poor image quality evaluation of Structural SIMilarity (SSIM) for blurred images and high texture images, this paper proposed a new algorithm for full reference image quality assessment based on phase congruency structural similarity. The new method kept luminance function and contrast function in SSIM, while replaced the structural function of SSIM with phase congruency function. Then the luminance, contrast and phase congruency information were combined to evaluate the image quality. The linear correlation coefficient and the Spearman rank correlation coefficient between the results of the proposed method on LIVE database and the subjective quality measurements were 0.9501 and 0.9362 respectively. The experimental results demonstrate that phase congruency obtains more structural information of the image. The proposed method can obtain better performances and provide more accurate assessment results on burred and high texture images quality.

Concerning the low speed and low efficiency of learning in robot soccer when cooperating between multi-robots, a cooperative Q learning method based on the mental model of π calculus was proposed, in which the mental states were defined as the field state, goal, intention, action, cooperation, request, expanding knowledge，capability judging and connected intention, etc, and the combinational reward function was constructed. The validity of method was verified through experiments.

lectronic auction is one of the methods of electronic commerce. A new sealed-bid electronic auction based on group signature and verifiable secret sharing scheme was proposed. In this protocol, multi-auctioneers participated in auction synchronously, and all auctioneers shared one key, therefore the bidder needed only one encryption in bidding, and the computation was independent of the number of auctioneers. In addition, the identity of the winner was identified by group manager according to signature of the winner’s bidding message, therefore after registering once, bidder could participate in many auctions synchronously without disclosing his identity.