Goertek Inc.

Fuli Xie

Yifan Zhang

Jie Liu

Jifeng Tian

Shunran Di

Pengcheng Su

Yifan Yang

A computer vision-based anomaly detection method and device and an electronic apparatus are disclosed. The method comprises: dividing a target picture into at least two feature regions according to different region features of the target picture, and forming training sets respectively using the feature regions corresponding to each target picture; selecting generative adversarial networks GAN as network models to be used, and training GAN network models with the training sets of different feature regions to obtain GAN network models corresponding to different feature regions; and when performing anomaly detection, performing same feature region division on a target picture to be detected, inputting different feature regions of the target picture to be detected into corresponding GAN network models to obtain a generated picture, and performing pixel value-based difference detection on the generated picture and the target picture to be detected.

Computer vision-based anomaly detection method, device and electronic apparatus

A method and device for small sample defect classification and a computing equipment are disclosed. The method comprises: separating a target to be tested into parts, and segmenting an original image of the target to be tested into at least two sub-images containing different parts according to the separated parts; establishing small sample classification models with respect to each sub-image and the original image respectively, and obtaining a classification result of each sub-image and a classification result of the original image by using corresponding classification models, wherein the classification result includes a defect category and a corresponding category probability; and determining and outputting a defect category of the target to be tested according to classification results of all the sub-images and the original image.

Method and device for small sample defect classification and computing equipment

A product defect detection method, device and system are disclosed. The method comprises: acquiring a sample image of a product, extracting candidate image blocks probably including a product defect from the sample image, and extracting preset shape features corresponding to the candidate image blocks and texture features corresponding to the candidate image blocks; training a first-level classifier using the preset shape features to obtain a first-level classifier that can further screen out target image blocks probably including a product defect from the candidate image blocks; training a second-level classifier using the texture features to obtain a second-level classifier that can correctly identify a product defect; and when performing product defect detection, inputting preset shape features of candidate image blocks extracted from a product image into the first-level classifier, and then inputting texture features of obtained target image blocks into the second-level classifier to detect a defect in the product.

Product defect detection method, device and system

A method and a wearable device are provided. The method includes providing a swimming mode in the wearable device, and storing standard swimming stroke data that have been collected in advance as corresponding template data, when a monitoring process starts, activating the swimming mode according to an instruction given by a user who will immediately enter water, and after the swimming mode has been activated, controlling a sensor to collect swimming stroke data of the user; obtaining test data for identifying a swimming state of the user from the swimming stroke data; and matching the test data with each template data, when the test data successfully matches the template data, identifying the swimming state of the user to be the swimming state that corresponds to the template data.

Method for monitoring swimming state by means of wearable device, and wearable device

The application discloses a method for monitoring a user gesture and a wearable device. The method comprises: providing an inertial sensor in a wearable device, the wearable device being located on the head of a user when being worn; monitoring movement data of the head of the user in real time, by using the inertial sensor, when the user is wearing the wearable device; conducting gesture solving by using the movement data to obtain gesture data of the head of the user; determining whether a head gesture of the user is a correct gesture according to the gesture data and a preset strategy; and sending a reminder to the user when the head gesture of the user is an incorrect gesture.

Method for monitoring user gesture of wearable device

A following method and device for an unmanned aerial vehicle and a wearable device are provided. The following method comprises: installing a plurality of receiving sensors on the unmanned aerial vehicle, wherein the plurality of receiving sensors match with one transmitting sensor in a smart control device at the user side; receiving a distance signal transmitted by the user in real time by using the receiving sensors, and calculating a relative position of the unmanned aerial vehicle with respect to the user according to the distance signal; and adjusting the horizontal position of the unmanned aerial vehicle according to the relative position, so that the relative position of the unmanned aerial vehicle with respect to the user agrees with a preset position, to realize automatic following of the unmanned aerial vehicle.

Following method and device for unmanned aerial vehicle and wearable device

A method and device for face tracking and a smart terminal. The method includes: collecting a frame of an image in a video stream and conducting face detection and identification, to identify a target face; determining a position of a window to be tracked that contains the target face according to the identified target face, and extracting an edge feature point in the window to be tracked of the reference frame; determining an initial position of a window to be tracked on the current frame in the video stream, and extracting an edge feature point in the window to be tracked of the current frame; calculating a relative displacement between the edge feature point of the reference frame and the edge feature point of the current frame; and adjusting the initial position of the window to be tracked of the current frame by using the relative displacement.

Growing community of inventors

Weifang, China

Fuli Xie