Gesture recognition is a new human-machine interface method implemented by pattern recognition(PR).In order to
assure robot safety when gesture is used in robot control, it is required to implement the interface reliably and accurately.
Similar with other PR applications, 1) feature selection (or model establishment) and 2) training from samples, affect the
performance of gesture recognition largely. For 1), a simple model with 6 feature points at shoulders, elbows, and hands,
is established. The gestures to be recognized are restricted to still arm gestures, and the movement of arms is not
considered. These restrictions are to reduce the misrecognition, but are not so unreasonable. For 2), a new biological
network method, called lobe component analysis(LCA), is used in unsupervised learning. Lobe components,
corresponding to high-concentrations in probability of the neuronal input, are orientation selective cells follow Hebbian
rule and lateral inhibition. Due to the advantage of LCA method for balanced learning between global and local features,
large amount of samples can be used in learning efficiently.
In factory-automation, in order to avoid collision between human-bodies and autonomous mobile machines, a stereo-camera based method was proposed to implement an intelligent sensing method for human-bodies. An experimental system for this purpose was complemented, and an evaluation experiment was performed. The experiment shows that the accurate results were obtained in the case that no object other than human-body enters/exits to the monitored area.
As a prospective intelligent sensing method for Autonomous Guided Vehicle (AGV), machine vision is expected to have balanced ability of covering a large space and also recognizing details of important objects. For this purpose, the proposed hybrid machine method here combines the stereo vision method and the traditional 2D method. The former implements coarse recognition to extract object over a large space, and the later implement fine recognition about some sub-areas corresponding to important and/or special objects. This paper is mainly about the coarse recognition. In order to extract objects in the coarse recognition stage, the disparity image calculated according to stereo vision principle is segmented by two consequent steps of region expansion and convex split. Then the 3D measurement about the rough positions and sizes of extracted objects is performed according to the disparity information of the corresponding segmentation, and is used for recognizing the objects' attributes by means of pattern learning/recognition. The attribute information resulted is further used to assist fine recognition in the way of performing gaze control to input suitable image of the interested objects, or to directly control AGV's travel. In our example AGV application, some navigation-signs are introduced to indicate the travel route. When the attribute shows that the object is a navigation-sign, the 3D measurement is used to gaze the navigation-sign, in order for the fine recognition to analyze the specific meaning by means of traditional 2D method.