Beihang University

Megvii (beijing) Technology Co., Ltd.

Beijing Kuangshi Technology Co., Ltd.

Xiangyu Zhang

Deyuan Zhang

Xinggang Jiang

Tong Yang

Xinyu Zhou

Shenliang Yang

Daxi Geng

Mengxiao Lin

Yihui He

Zhenghui Lu

He Sui

Xun Li

Wenlong Xin

Provided are image processing method and apparatus for processing an input image using a convolutional neural network system, and a computer-readable storage medium. The convolutional neural network system that includes an input layer, an intermediate layer and an output layer, the image processing method includes: receiving the input image via the input layer; extracting image features of the input image via the intermediate layer; and outputting processing results for the input image via the output layer, wherein the intermediate layer includes at least one network block each of which includes a first convolutional layer, a first grouping rearrangement layer and a second convolutional layer that are cascaded.

Image processing method, image processing apparatus, and computer-readable storage medium

The present disclosure provides a target detection method, target detection system and non-volatile storage medium. The target detection method includes: acquiring an image to be detected and anchor parameters of preset type number, wherein the anchor parameters are parameters of an anchor set on the image to be detected, and each type of anchor parameters include an anchor scale and an anchor aspect ratio; inputting the image to be detected and the anchor parameters into a target detection model; and carrying out target detection on the image to be detected on the basis of the anchor parameters by the target detection model to obtain a detection result, the detection result including a category and/or a position of a target object included in the image to be detected.

Target detection method, system, and non-volatile storage medium

An ultrasonic peening-type integrated machining method for cutting and extrusion includes: applying transverse ultrasonic vibration or a vibration component, which is vertical to a cutting speed direction to a cutting tool on a machine tool; setting a cutting parameter and an ultrasonic vibration parameter such that a dynamic negative clearance angle is generated in a cutting procedure and a flank face of the cutting tool conducts ultrasonic peening extrusion on the surface of the workpiece; setting an extrusion overlap ratio; setting a wear standard of flank faces extruded by the cutting tool; controlling a vibration cutting trajectory phase difference of the cutting tool during two adjacent rotations; and turning on the machine tool in order to ensure that cutting and surface extrusion strengthening of the workpiece are completed in one procedure without separate strengthening procedures. The method conducts extrusion strengthening on the surface of the workpiece while cutting the workpiece.

Ultrasonic peening-type integrated machining method of cutting and extrusion

Provided are neural network-based image processing method and apparatus, and a computer-readable storage medium. The image processing method includes: inputting an image into an optimized neural network; extracting, by the optimized neural network, image features of the image; and outputting the image features, wherein the optimized neural network is obtained by performing a first optimization process on at least one sub-layer in a pre-trained initial neural network, each sub-layer of the at least one sub-layer includes a convolutional layer, and the first optimization process comprises: for each sub-layer of the at least one sub-layer, determining one or more channels to be removed from a filter of the convolutional layer and removing said one or more channels, and optimizing parameters of remaining channels in the filter of the convolutional layer, so that error of output features of each optimized sub-layer is minimized.

Image processing method and apparatus, and computer-readable storage medium

A high-speed precision interrupted ultrasonic vibration cutting method includes steps of: (1) installing an ultrasonic vibration apparatus on a machine tool, and stimulating a cutting tool to generate a transverse vibration, so as to realize varieties of machining processes; (2) realizing an interrupted cutting process by setting cutting parameters and vibration parameters to satisfy an interrupted cutting conditions; and (3) turning on the ultrasonic vibration apparatus and the machine tool, and starting a high-speed precision interrupted ultrasonic vibration cutting process. High-speed precision interrupted ultrasonic vibration cutting is able to be realized through the above steps during machining of difficult-to-machine materials in aviation and aerospace fields. A cutting speed is enhanced significantly, and exceeds a critical cutting speed of a conventional ultrasonic vibration cutting method and an elliptical ultrasonic vibration cutting method and even a high speed range of a traditional cutting method.

High-speed precision interrupted ultrasonic vibration cutting method

Growing community of inventors

Beijing, China

Xiangyu Zhang