Abstract: A hierarchical system for detecting an object with parallel architecture and a hierarchical method thereof is disclosed. The system includes at least one image-retrieving device retrieving at least an image and searching a plurality of obstacle position images in it. The image-retrieving device is electrically connected with an image-processing device to receive the obstacle position images transmitted by the image-retrieving device, uses parallel architecture classification to obtain at least one object image and a plurality of cropping frames thereof from the obstacle position images, synchronously separates the cropping frames to retrieve characteristic values of each cropping frame, uses convolutional neural network to simultaneously recognize the characteristic values of each cropping frame, and searches and outputs the correct cropping frame from the object image, thereby immediately detecting the object outside a vehicle and obtaining the cropping frame of the object to avoid detection error.

Abstract: A hierarchical system for detecting an object with parallel architecture and a hierarchical method thereof is disclosed. The system includes at least one image-retrieving device retrieving at least an image and searching a plurality of obstacle position images in it. The image-retrieving device is electrically connected with an image-processing device to receive the obstacle position images transmitted by the image-retrieving device, uses parallel architecture classification to obtain at least one object image and a plurality of cropping frames thereof from the obstacle position images, synchronously separates the cropping frames to retrieve characteristic values of each cropping frame, uses convolutional neural network to simultaneously recognize the characteristic values of each cropping frame, and searches and outputs the correct cropping frame from the object image, thereby immediately detecting the object outside a vehicle and obtaining the cropping frame of the object to avoid detection error.

Abstract: An adaptive device and an adaptive method for classifying objects with parallel architecture are provided. The method stores a plurality of scene parameters and a plurality of classifier parameters. The method retrieves at least one image datum and then drags frames to enclose a plurality of obstruction images of the image datum and decides a frame range according to a range of each obstruction image. The method uses a plurality of image processing units to respectively calculate a plurality of obstruction characteristic data of the obstruction images in a one-by-one parallel processing way, and chooses and calculates the scene parameters and the classifier parameters corresponding to the obstruction characteristic data to obtain a plurality of classification data. When the method determines that the classification data belongs to the obstruction classification preset, positions of enclosed obstruction images are outputted to achieve real time detection for obstructions.