International Business Machines Corporation

Hong Bing Zhang

Dan Zhang

Xue Ping Liu

Fan Li

Yuan Yuan Ding

Chao Xin

Tian Tian Chai

Kun Yan Yin

Zhuo Jp Cai

Yun Jing Zhao

Xu Min

Yi Chen Zhong

Jing Wu

Nuo Xu

Patrick Joseph O'Sullivan

Edith H Stern

Barry Edward Willner

Ming Jin Chen

Wei Peng Huang

Hao Kai Zhang

Huan Wang

Zhong Fang Yuan

Tong Liu

Hong Yu Chen

Yang Liu

Guoqiang Hu

Yi Zhi Yao

Sheng Nan Zhu

Chao Yu

Miao Guo

Yu Luo

Xin Fang Hao

Guang Qing Zhong

Teng Sun

Zhi Peng

Shen Ming Tao

Wang Xiao

De Bo Xiong

According to one embodiment, a method, computer system, and computer program product for predicting the movement intentions of ships is provided. The present invention may include obtaining binocular camera visual data of a body of water; identifying physical objects in the body of water; generating feature point clouds of the physical objects in the body of water; performing instance segmentation on the generated feature point clouds; analyzing the generated feature point clouds; predicting the movement intentions of identified ships in the body of water based on the analyzed feature point clouds; and displaying the predicted movement intentions of the identified ships in the body of water on an augmented reality device.

AR and deep learning intersection ship route predictor

In an aspect for generating a 2-dimensional (2D) building mapping, a computer-implemented method may include one or more processors configured for receiving scanning data in a first file format corresponding to 3-dimensional (3D) aerial Light Detection and Ranging (LiDaR) images. Further, the method may include transforming the first file format to a second file format and transmitting the scanning data to a building semantic segmentation component. Further, the computer-implemented method may include generating semantic segmentation data corresponding to building structures defined by point clusters; generating instance segmentation data corresponding to top surfaces of the building structures; generating building boundary data for each one of the point clusters based on one or more of the semantic segmentation data and the instance segmentation data; and processing the building boundary data to generate a 2D building mapping comprising refined boundary lines for each of the point clusters.

Generating 2D mapping using 3D data

A method for restoration of a kinetic event using video. The method includes obtaining video involving the kinetic event including a plurality of frames. An absolute location of a frame of the plurality of frames is determined. Movement of a feature point cloud corresponding to an object in motion in the plurality of frames is analyzed. A 3D object model with substantially similar dimensions to the object in motion is selected. The 3D object model is displayed emulating the analysed movement on the 3D map based on the absolute location.

Restoration of a kinetic event using video

Analysis of edge closures of metal surface particles based on a graph structure.

Analyzing edge closures of metal surface particles based on graph structures

A method, a computing system and a computer program product for collecting and labelling images includes capturing a video of an object with a camera. A movement trace of a pointer is recorded that outlines the object while capturing the video of the object. Further included is generating a labeled image based at least on the captured video of the object and the recorded movement trace of the pointer. The labeled image includes the object and a line that surrounds the object.

Image collection and labelling using computer system and analysis

Technology for inspection for detecting a defect of a printed matter using machine logic informed by machine learning. Some embodiments of the present invention may include one, or more, of the following features: (i) generates defect datasets; (ii) generates defect libraries; (iii) uses the generated defect libraries for deep learning training; and (iv) uses machine learning to detect defects using computer code (for example, a *.jpg format file) corresponding to an image of a piece of printed matter instead of using a visual image (that is, an image of the type that is created when a person takes a picture using a traditional film camera).

Automatically generating defect data of printed matter for flaw detection

An approach is provided in which the approach receives an image that includes multiple image points and constructs a plane in the image based on a first subset of the plurality of image points. The approach identifies a second subset of the image points that belong to the plane and are not part of the first subset of image points, and removes the first subset of image points and the second subset of image points form the image points. The approach annotates the remaining subset of image points in the image.

Three-dimensional segmentation annotation

A method for detecting and labeling a target object in a 2D image includes receiving a plurality of 2D images from a visual sensor, manually marking points of the target object on each of the 2D images, generating from the 2D images a 3D world coordinate system of the environment surrounding the target object, mapping each of the marked points on the 2D images to the 3D world coordinate system using a simultaneous localization and mapping (SLAM) engine, automatically generating a 3D bounding box covering all the marked points mapped to the 3D world coordinate system, mapping the 3D bounding box to each of the 2D images, generating a label for the target object on each of the 2D images using a machine learning object detection model, and training the machine learning object detection model based on the generated label for the target object.

AR-based labeling tool for 3D object detection model training

In an approach for detecting vehicle identity and analyzing damage status using a single video, a processor provides an instruction for taking a video of a vehicle for a damage evaluation. A processor receives the video of the vehicle for the damage evaluation. A processor verifies the vehicle in the video being the same vehicle for the damage evaluation. A processor evaluates a damage status of the vehicle. A processor outputs a damage report based on the damage status of the vehicle.

Detecting vehicle identity and damage status using single video analysis

A system, method, and computer program product for implementing video action recognition is provided. The method includes receiving a video stream comprising user movement actions. Skeleton points associated with a video representation of a user executing the user movement actions are extracted and categorized with respect to multiple digital levels. Initial visual windows points are generated within video frames and an average movement distance for the group of skeleton points are determined with respect to the video frames. In response, sizes for the visual windows are adjusted and feature vectors are extracted from the group of skeleton points. Point coordinates of the skeleton points are extracted and linked with the feature vectors. A convolutional neural network associated with linking the feature vectors with the point coordinates is generated and the video stream is enabled with respect to video action recognition associated with accurate presentation of the video stream.

Video action recognition and modification

A computer-implemented method for annotating images is disclosed. The computer-implemented method includes generating a saliency map corresponding to an input image, wherein the input image is an image that requires annotation, generating a behavior saliency map, wherein the behavior saliency map is a saliency map formed from an average of a plurality of objects contained within respective bounding boxes of a plurality of sample images, generating a historical saliency map, wherein the historical saliency map is a saliency map formed from an average of a plurality of tagged objects in the plurality of sample images, fusing the saliency map corresponding to the input image, the behavior saliency map, and the historical saliency map to form a fused saliency map, and generating, based on the fused saliency map, a bounding box around an object in the input image.

Automatic image annotations

Computer automated interactive activity recognition based on keypoint detection includes retrieving, by one or more processors, a temporal sequence of image frames from a video recording. The one or more processors identify first and second keypoints in each of the image frames in the temporal sequence using machine learning techniques. The first keypoints are associated with an object in the temporal sequence of image frames while the second keypoints are associated with an individual interacting with the object. The one or more processors combine the first keypoints with the second keypoints and extract spatial-temporal features from the combination that are used to train a classification model based on which interactive activities can be recognized.

Computer automated interactive activity recognition based on keypoint detection

In an approach for JAVA Virtual Machine (JVM) heap memory tuning, one or more computer processors obtain a feature vector of an application running on the JVM. The one or more computer processors input the feature vector to a predictive model trained with historical application data collected in one or more production environments. The one or more computer processors receive an output of the predictive model based on the feature vector with at least one memory tuning recommendation for the JVM. The one or more computer processors tune the memory of the JVM based on the at least one memory tuning recommendation.

Machine-learning based heap memory tuning

A method, computer system, and a computer program product for analyzing visual defects is provided. The present invention may include generating a template image. The present invention may include capturing a test image. The present invention may include performing an image registration between the template image and the test image. The present invention may include generating a registered test image. The present invention may include performing an image difference analysis between the registered test image and the template image. The present invention may include generating a differential image. The present invention may include synthesizing the registered, differential image, and template image. The present invention may include generating a synthetic image. The present invention may include inputting the synthetic image into a multi-scale detection network. The present invention may include generating a defect map.

Determining image defects using image comparisons

Disclosed embodiments provide techniques for estimating crowd flow rate. Video frames are obtained from a crowd scene. Groups of consecutive video frames form a time window. Crowd flow rate through the field of view of the camera is analyzed by estimating a total number of people contained within at least one frame of a time window. A subset of the people within the frame are identified as a group of tracker candidates. The tracker candidates are monitored throughout the time window, and the time when the tracker candidates exit the field of view of the camera is used to estimate a crowd flow rate for the number of people passing through the field of view of the camera in a given time interval. Thus, disclosed embodiments can improve the technical field of crowd flow rate estimation.

Growing community of inventors

Beijing, China

Hong Bing Zhang