This paper presents a novel technique for the segmentation of data W = [w1· · · wn] ⊂ RDdrawn from a union u = ∪Mi=1of subspaces {Si}Mi=1. First, an existing subspace segmentation algorithm is used to perform an initial data clustering {Ci}Mi=1, where Ci= {wi1· · ·wik} ⊂ W is the set of data from the ithcluster. Then, a local subspace LSiis matched for each Ciand the distance dijbetween LSiand each point wij∊ Ciis computed. A data-driven threshold η is computed and the data points (in Ci) whose distances to LSiare larger than η are eliminated since they are considered as outliers or erroneously clustered data points in Ci. The remaining data points Ci⊂ Ciare considered to be coming from the same subspace with high confidence. Then, {Ci}Mi=1are used in unsupervised way to train a convolution neural network to obtain a deep learning model, which is in turn used to re-cluster W. The system has been successfully implemented using the MNIST dataset and it improved the segmentation accuracy of a particular algorithm (EnSC-ORGEN) from 93.79% to 96.52%.

There are many industrial robot manufacturers providing industrial robots with its controller and software. With safety and real-time operation concerns, these commercial robots have restrictive programming facilities. A few processes may run concurrently. Old style, imperative programming languages provided by robot manufacturers make software development difficult and expensive. This paper presents a software design based on server-client architecture in a modular form. At the server side, the controller of the robot manages the robot according to commands received from Ethernet connection. At the client side, the programmer may develop custom software by using robot API. It allows the user to manage robot by sending commands through the Ethernet connection. The design details and an application implemented by using Kawasaki 6-axis robot are given.

This paper presents a people counting system as an application of a people counting method. The method uses depth and vision data captured by a low-cost Kinect sensor. The sensor is placed perpendicular to the ceiling. The perception of the people is achieved by using water filling method. A new approach called as people tracking increases the performance of the people counting system. Some real applications are given to show the efficiency of the proposed approach.

The studies on mirror neurons observed in monkeys indicate that recognition of other's actions activates neural circuits that are also responsible for generating the very same actions in the animal. The mirror neuron hypothesis argues that such an overlap between action generation and recognition can provide a shared worldview among individuals and be a key pillar for communication. Inspired by these findings, this paper extends a learning by demonstration method for online recognition of observed actions. The proposed method is shown to recognize and generate different reaching actions demonstrated by a human on a humanoid robot platform. Experiments show that the proposed method is robust to both occlusions during the observed actions as well as variances in the speed of the observed actions. The results are successfully demonstrated in an interactive game with the iCub humanoid robot platform.