Building a mathematical model of uneven illumination and contrast is difficult, even impossible. This paper presents a novel image balancing method for a satellite image. The method adjusts the mean and standard deviation of a neighborhood at each pixel and consists of three steps, namely, elimination of coarse light background, image balancing, and max-mean-min radiation correction. First, the light background is roughly eliminated in the frequency domain. Then, two balancing factors and linear transformation are used to adaptively adjust the local mean and standard deviation of each pixel. The balanced image is obtained by using a color preserving factor after max-mean-min radiation correction. Experimental results from visual and objective aspects based on images with varying unevenness of illumination and contrast indicate that the proposed method can eliminate uneven illumination and contrast more effectively than traditional image enhancement methods, and provide high quality images with better visual performance. In addition, the proposed method not only restores color information, but also retains image details.
The arithmetic optimization algorithm (AOA) is a new metaheuristic algorithm inspired by arithmetic operators (addition, subtraction, multiplication, and division) to solve arithmetic problems. The algorithm is characterized by simple principles, fewer parameter settings, and easy implementation, and has been widely used in many fields. However, similar to other meta-heuristic algorithms, AOA suffers from shortcomings, such as slow convergence speed and an easy ability to fall into local optimum. To address the shortcomings of AOA, an improved arithmetic optimization algorithm (IAOA) is proposed. First, dynamic inertia weights are used to improve the algorithm’s exploration and exploitation ability and speed up the algorithm’s convergence speed; second, dynamic mutation probability coefficients and the triangular mutation strategy are introduced to improve the algorithm’s ability to avoid local optimum. In order to verify the effectiveness and practicality of the algorithm in this paper, six benchmark test functions are selected for the optimization search test verification to verify the optimization search ability of IAOA; then, IAOA is used for the parameter optimization of support vector machines to verify the practical ability of IAOA. The experimental results show that IAOA has a strong global search capability, and the optimization-seeking capability is significantly improved, and it shows excellent performance in support vector machine parameter optimization.
Person Reid is a challenging task for two factors, first one is background interference, such as changes in light, weather, posture, and camera position. Second is domain adaptive capacity, such as model train by market1501 achieve the same performance on Duke dataset. To solve the above problems, we come up with adopt human semantic to remove clutter from unwanted background information, is naturally a better alternative compare with bounding box, we adopt Local Regions Representation to extra the image features, which can preeminently improve the representation of local feature and global feature. Our proposed CSReID integrates human semantic and Local Regions Representation in person re-identification and not need to train on the evaluation dataset can achieve state of the art cross-modal performance.