We present a novel color transfer method for portraits by exploring their high-level semantic information. Given a source portrait image, we first use Face++ to search images with similar poses as the input from a database, and the user chooses one satisfactory image from the results as the target. The database consists of a collection of portrait images downloaded from the Internet, and each of them is manually segmented using image matting as a preprocessing step. Second, we extract portrait foregrounds from both source and target images. Third, the system extracts the semantic information, such as faces, eyes, eyebrows, lips, teeth, etc., from the extracted foreground of the source using image matting algorithms. After that, we perform color transfer between corresponding parts with the same semantic information. We get the final transferred result by seamlessly compositing different parts together using alpha blending. Experimental results show that our semantics-driven approach can generate better color transfer results for portraits than previous methods and provide users a new means to retouch their portraits.

The recognition of impassable terrain plays a vital role in the motion planning of a mobile robot, which generally relies on expensive sensors such as stereo vision cameras. This paper proposes a rapid impassable terrain recognition algorithm based on hypotheses testing theory using low-cost range finders with different diffusion angles. In this algorithm, a slope estimation model using two range finders mounted on different heights is first established, where the influence of the diffusion angle of the range sensor is considered. To deal with inaccurate measuring from low cost range finders, the hypothesis testing theory is then applied to judge whether there is an impassible terrain approaching, where the historical slope estimation results are treated as a sample set of the same slope, and the judgement of impassible terrain is then made based on the sampling set rather than the concurrent slope estimation. So the robot is only required to count the number of slope estimation that support the determination of a terrain as being impassible, and the judgement is confirmed only when that number is larger than a precisely designed threshold value. Then the stable recognition for impassable terrain would be acquired while the risk of wrong judgement is limited. The experiments' results indicate that this algorithm can provide a reliable recognition of impassable terrain using lower cost range finders with different diffusion angles with minimal computation.

No abstract

Visual tracking is a key research area in computer vision, as tracking technology is increasingly being applied in daily life, it has high-research significance. Visual tracking technology usually faces various challenging interference factors, among which, a similar background is one of the factors that has a greater impact on the tracking process. Kernelized Correlation Filter (KCF) tracking algorithm can track targets quickly by using circulant matrix, and has good tracking effect, so it is widely used in the tracking field. However, when the target is interfered by similar objects, the filter template in KCF cannot effectively distinguish between the target and the interfering object. This is because the filter only uses the texture gradient feature as the description object of the target, which will make the KCF algorithm extremely sensitive to the change of the target; therefore, the filter has difficultly making a judgment in the unstable scene, cannot accurately describe the target state, and finally leads to tracking failure. Therefore, this paper fuses Color Names (CN) on the basis of the original Histogram of Oriented Gradients (HOG) feature of KCF, which can obtain a more comprehensive feature representation, and realize the application of combined features to improve the anti-interference ability of KCF in complex scenes. In addition, this paper also uses the peak response of correlation filtering as the judgment condition to determine whether the current tracking result is stable. When the filter is in an unstable tracking state, the proposed algorithm will select the value with high confidence from its multiple responses as the candidate target of the Siamese network, and the deep learning network is used as the incremental learning method of the filter. The Channel Attention is introduced into the network layer, so that the network can adaptively reason and adjust the extracted universal features, and the enhanced feature information is used as the final discriminant basis. Finally, according to the response, the target with the smallest error compared with the target template is selected from multiple candidate targets as the final tracking result. The experimental results show that the average accuracy and average success rate of the proposed algorithm are significantly improved compared with the classical tracking algorithm, especially in dealing with similar target interference.