Method for providing power-off command to an automatic apparatus within proximity of a human and control apparatus employing the method
AssigneeShenzhen Fugui Precision Ind. Co., Ltd.
InventorsChang-Ching Liao, Shao-Wen Wang, Shih-Cheng Wang
Life of this patent
Estimating the term…
Abstract
A method for ensuring safety of humans within operating area or in close proximity to an automatic apparatus is applied in and by a control apparatus. The control apparatus is coupled to one or more cameras arranged around the operating area of the automatic apparatus. The control apparatus uses deep learning techniques to analyze images captured by the cameras to determine whether there is a person in the operating area and powers off the automatic apparatus if any person is deemed present.
Claims6
A method for providing human-machine cross-over safety applied in a control device, the method comprising:
- capturing a plurality of images by a camera arranged in proximities to an operating area of an automatic apparatus, wherein the plurality of images comprise different characteristic poses and a plurality of operations of the automatic apparatus when no persons are present in the operating area, the different characteristic poses comprise a human being stretching, standing, bending, squatting, sitting, and climbing, and the different characteristic poses are produced by different people wearing different devices and work clothes when in close proximity to the automatic apparatus;
- training a neural network by the plurality of images;
- receiving an image captured by the camera;
- inputting the received image to the trained neural network;
- outputting an analyzing result of the received image using the trained neural network;
- and
- transmitting a power-off signal to the automatic apparatus if the image comprises at least one person in the operating area.
A control apparatus coupled to a camera and an automatic apparatus, the control apparatus comprising:
- a processor;
- and
- a memory for storing at least one computer program, wherein the computer program comprises instructions which are executed by the processor, and performs the following steps:
- capturing a plurality of images by a camera arranged in proximities to an operating area of an automatic apparatus, wherein the plurality of images comprise different characteristic poses and a plurality of operations of the automatic apparatus when no persons are present in the operating area, the different characteristic poses comprise a human being stretching, standing, bending, squatting, sitting, and climbing, and the different characteristic poses are produced by different people wearing different devices and work clothes when in close proximity to the automatic apparatus;
- training a neural network by the plurality of images;
- receiving an image captured by the camera;
- inputting the received image to the trained neural network;
- outputting an analyzing result of the received image using the trained neural network;
- and
- transmitting a power-off signal to the automatic apparatus if the image comprises at least one person in the operating area.
Dependencies are inferred from the claim text.