Shenyang Institute of Automation

About: Shenyang Institute of Automation is a facility organization based out in Shenyang, China. It is known for research contribution in the topics: Robot & Mobile robot. The organization has 2079 authors who have published 1670 publications receiving 11414 citations.

Survey of Robot 3D Path Planning Algorithms

Abstract: Robot 3D three-dimension path planning targets for finding an optimal and collision-free path in a 3D workspace while taking into account kinematic constraints including geometric, physical, and temporal constraints. The purpose of path planning, unlike motion planning which must be taken into consideration of dynamics, is to find a kinematically optimal path with the least time as well as model the environment completely. We discuss the fundamentals of these most successful robot 3D path planning algorithms which have been developed in recent years and concentrate on universally applicable algorithms which can be implemented in aerial robots, ground robots, and underwater robots. This paper classifies all the methods into five categories based on their exploring mechanisms and proposes a category, called multifusion based algorithms. For all these algorithms, they are analyzed from a time efficiency and implementable area perspective. Furthermore a comprehensive applicable analysis for each kind of method is presented after considering their merits and weaknesses.

DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal

Abstract: Shadow removal is a challenging task as it requires the detection/annotation of shadows as well as semantic understanding of the scene. In this paper, we propose an automatic and end-to-end deep neural network (DeshadowNet) to tackle these problems in a unified manner. DeshadowNet is designed with a multi-context architecture, where the output shadow matte is predicted by embedding information from three different perspectives. The first global network extracts shadow features from a global view. Two levels of features are derived from the global network and transferred to two parallel networks. While one extracts the appearance of the input image, the other one involves semantic understanding for final prediction. These two complementary networks generate multi-context features to obtain the shadow matte with fine local details. To evaluate the performance of the proposed method, we construct the first large scale benchmark with 3088 image pairs. Extensive experiments on two publicly available benchmarks and our large-scale benchmark show that the proposed method performs favorably against several state-of-the-art methods.

Video Desnowing and Deraining Based on Matrix Decomposition

Abstract: The existing snow/rain removal methods often fail for heavy snow/rain and dynamic scene. One reason for the failure is due to the assumption that all the snowflakes/rain streaks are sparse in snow/rain scenes. The other is that the existing methods often can not differentiate moving objects and snowflakes/rain streaks. In this paper, we propose a model based on matrix decomposition for video desnowing and deraining to solve the problems mentioned above. We divide snowflakes/rain streaks into two categories: sparse ones and dense ones. With background fluctuations and optical flow information, the detection of moving objects and sparse snowflakes/rain streaks is formulated as a multi-label Markov Random Fields (MRFs). As for dense snowflakes/rain streaks, they are considered to obey Gaussian distribution. The snowflakes/rain streaks, including sparse ones and dense ones, in scene backgrounds are removed by low-rank representation of the backgrounds. Meanwhile, a group sparsity term in our model is designed to filter snow/rain pixels within the moving objects. Experimental results show that our proposed model performs better than the state-of-the-art methods for snow and rain removal.

An Incremental Learning Method Based on Probabilistic Neural Networks and Adjustable Fuzzy Clustering for Human Activity Recognition by Using Wearable Sensors

Abstract: Human activity recognition by using wearable sensors has gained tremendous interest in recent years among a range of health-related areas. To automatically recognize various human activities from wearable sensor data, many classification methods have been tried in prior studies, but most of them lack the incremental learning abilities. In this study, an incremental learning method is proposed for sensor-based human activity recognition. The proposed method is designed based on probabilistic neural networks and an adjustable fuzzy clustering algorithm. The proposed method may achieve the following features. 1) It can easily learn additional information from new training data to improve the recognition accuracy. 2) It can freely add new activities to be detected, as well as remove existing activities. 3) The updating process from new training data does not require previously used training data. An experiment was performed to collect realistic wearable sensor data from a range of activities of daily life. The experimental results showed that the proposed method achieved a good tradeoff between incremental learning ability and the recognition accuracy. The experimental results from comparison with other classification methods demonstrated the effectiveness of the proposed method further.