Patents by Inventor Liuan WANG
Liuan WANG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240070695Abstract: The disclosure relates to a method, device and storage medium for processing a target track. According to an embodiment, the method comprises: determining a candidate customer track set of a receipt data group corresponding to one of a plurality of shopping receipts; counting, for each track, the number of sold items matching the track in location in a sold item set indicated by the receipt data group, as a first location matching count of the track; counting, for each track, the number of sold items matching track points of interest in a set of track points of interest of the track in location in the sold item set, as a second location matching count of the track; and determining a customer track corresponding to the receipt data group based on first location matching counts and second location matching counts of a plurality of tracks in the candidate customer track set.Type: ApplicationFiled: July 21, 2023Publication date: February 29, 2024Applicant: Fujitsu LimitedInventors: Liuan WANG, Huigang ZHANG, Ping WANG, Jun SUN
-
Publication number: 20240070881Abstract: A method for multi-target multi-camera tracking includes: performing multi-target tracking on a video captured by each of multiple cameras, to extract a tracklet for each target appearing in the video, wherein multiple tracklets for multiple targets are extracted on the basis of multiple videos; extracting a feature for each tracklet; determining orientation of each tracklet based on orientation of the target relative to the camera; dividing the multiple tracklets into multiple groups based on the determined orientations; performing clustering on tracklets in each group based on the extracted features, such that tracklets corresponding to the same target are aggregated into an initial set; performing merging among initial sets obtained by performing clustering on respective groups, such that tracklets corresponding to the same target and having different orientations are merged into a final set; and using the tracklets in the final set as tracking information for the corresponding target.Type: ApplicationFiled: August 25, 2023Publication date: February 29, 2024Applicant: Fujitsu LimitedInventors: Huigang ZHANG, Ping WANG, Liuan WANG, Jun SUN
-
Publication number: 20240037757Abstract: The present disclosure relates to a method, device and storage medium for post-processing in multi-target tracking. According to an embodiment of the present disclosure, the method comprises making attempts to split a tracklet indicative of a trajectory of a single target by performing operations of: determining a re-identification feature set of an image patch sequence by determining a re-identification feature of each image patch in the image patch sequence of the tracklet; determining whether a candidate identification switch image patch is present in the tracklet based on feature similarities of a plurality of re-identification feature pairs in the re-identification feature set; in a case where a determination result is “yes”, verifying whether it is credible that identification-switch has occurred at the candidate identification switch image patch; and in a case where a verification result is “credible”, splitting the tracklet into two tracklets based on the candidate identification switch image patch.Type: ApplicationFiled: July 11, 2023Publication date: February 1, 2024Applicant: Fujitsu LimitedInventors: Ping WANG, Liuan WANG, Jun SUN
-
Publication number: 20240029398Abstract: A method for multi-target multi-camera tracking includes: performing multi-target tracking on an image sequence captured by each of a plurality of cameras, to extract a tracklet for each target appearing in the image sequence; extracting a feature for each of the plurality of tracklets extracted; calculating a similarity between any two of the plurality of tracklets based on the extracted features, to establish a similarity matrix; performing clustering based on the similarity matrix so that tracklets potentially related to a target are aggregated in a set; sorting the tracklets in the set in a temporal order to generate a tracklet sequence; filtering the tracklets in the set based on at least one of a similarity, a time distance, and a space distance between the tracklets; and using the tracklets in the filtered set as tracking information for the corresponding target.Type: ApplicationFiled: July 21, 2023Publication date: January 25, 2024Applicant: Fujitsu LimitedInventors: Huigang ZHANG, Liuan WANG, Jun SUN
-
Publication number: 20240012146Abstract: The present disclosure relates to a method, an apparatus and a storage medium for multi-target multi-camera tracking. According to an embodiment of the present disclosure, the method comprises: determining an overall local target trajectory set including a local target trajectory set of each camera by performing single-camera multi-target tracking on a corresponding image sequence provided by each camera of a plurality of cameras; and determining a global target trajectory set for the plurality of cameras by performing multi-camera multi-target matching on the overall local target trajectory set; wherein determining the global target trajectory set comprises: determining a cluster matched global trajectory set by clustering local target trajectories; determining a cost-minimum path set by implementing a cost-minimum path algorithm on a directed graph; and merging corresponding trajectories in the cluster matched global trajectory set based on the cost-minimum path set.Type: ApplicationFiled: June 28, 2023Publication date: January 11, 2024Applicant: Fujitsu LimitedInventors: Liuan WANG, Huigang ZHANG, Ping WANG, Jun SUN
-
Patent number: 11586926Abstract: A method and apparatus of accelerating deep learning, and a deep neural network are provided. The method comprises: randomly initializing weights and biases of a deep neural network as n-bit fixed-point numbers; reducing data in a plurality of layers in the deep neural network that have calculation amounts are greater than a first predetermined threshold as m-bit fixed-point numbers, where m and n are integers and m<n, and maintaining data in remaining layers among the plurality of layers as n-bit fixed-point numbers; and training the deep neural network after the reducing, until convergence.Type: GrantFiled: January 18, 2019Date of Patent: February 21, 2023Assignee: FUJITSU LIMITEDInventors: Liuan Wang, Jun Sun
-
Patent number: 11386248Abstract: A method and a device for simulating atomic dynamics includes setting initial positions for multiple specific atoms in a specific scene; calculating, based on the initial positions, positions of the multiple specific atoms at each time in a first time series by utilizing a Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) configured with respect to the specific scene, as real positions; calculating, based on the initial positions, positions of the multiple specific atoms at the same time in the first time series by utilizing a generative adversarial network (GAN), as predicted positions; improving a configuration of the GAN based on the real positions and the predicted positions at a same time. Initial positions are settable for multiple atoms to be simulated in a scene; positions of the multiple atoms to be simulated are calculated at each time in a second time series in the scene by utilizing the improved GAN.Type: GrantFiled: November 26, 2019Date of Patent: July 12, 2022Assignee: FUJITSU LIMITEDInventors: Liuan Wang, Jun Sun
-
Publication number: 20220130137Abstract: A method and an apparatus for searching a neural network architecture comprising a backbone network and a feature network. The method comprises: a. forming a first search space for the backbone network and a second search space for the feature network; b. using a first controller to sample a backbone network model in the first search space, and using a second controller to sample a feature network model in the second search space; c. combining the first controller and the second controller by adding collected entropy and probability of the sampled backbone network model and feature network model to obtain a combined controller; d. using the combined controller to obtain a combined model; e. evaluating the combined model, and updating a combined model parameter according to an evaluation result; f. determining a verification accuracy of the updated combined model, and updating the combined controller according to the verification accuracy.Type: ApplicationFiled: January 10, 2022Publication date: April 28, 2022Applicant: Fujitsu LimitedInventors: Huigang ZHANG, Liuan WANG, Jun SUN
-
Patent number: 11227213Abstract: A device and a method for improving a processing speed of a neural network and applications thereof in the neural network where the device includes a processor configured to perform: determining, according to a predetermined processing speed improvement target, a dimension reduction amount of each of one or more parameter matrixes in the neural network obtained through training; preprocessing each parameter matrix based on the dimension reduction amount of the parameter matrix; and retraining the neural network based on a result of the preprocessing to obtain one or more dimension reduced parameter matrixes so as to ensure performance of the neural network meets a predetermined requirement. According to the embodiments of the present disclosure, it is possible to significantly improve the processing speed of the neural network while ensuring the performance of the neural network meets the predetermined requirement.Type: GrantFiled: October 31, 2017Date of Patent: January 18, 2022Assignee: FUJITSU LIMITEDInventors: Liuan Wang, Wei Fan, Jun Sun
-
Patent number: 11210561Abstract: A device and a method for electromagnetic field simulation are provided. The image processing device is to obtain, with a first resolution, a first electromagnetic field simulation result of a simulation region, and to derive a second electromagnetic field simulation result with a second resolution, according to the first electromagnetic field simulation result, using a model trained based on a deep learning method. The second resolution is higher than the first resolution.Type: GrantFiled: December 18, 2019Date of Patent: December 28, 2021Assignee: FUJITSU LIMITEDInventors: Rong Zhou, Liuan Wang, Jun Sun
-
Publication number: 20200193227Abstract: A device and a method for electromagnetic field simulation are provided. The image processing device is to obtain, with a first resolution, a first electromagnetic field simulation result of a simulation region, and to derive a second electromagnetic field simulation result with a second resolution, according to the first electromagnetic field simulation result, using a model trained based on a deep learning method. The second resolution is higher than the first resolution.Type: ApplicationFiled: December 18, 2019Publication date: June 18, 2020Applicant: FUJITSU LIMITEDInventors: Rong ZHOU, Liuan WANG, Jun SUN
-
Publication number: 20200175126Abstract: A method and a device for simulating atomic dynamics includes setting initial positions for multiple specific atoms in a specific scene; calculating, based on the initial positions, positions of the multiple specific atoms at each time in a first time series by utilizing a Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) configured with respect to the specific scene, as real positions; calculating, based on the initial positions, positions of the multiple specific atoms at the same time in the first time series by utilizing a generative adversarial network (GAN), as predicted positions; improving a configuration of the GAN based on the real positions and the predicted positions at a same time. Initial positions are settable for multiple atoms to be simulated in a scene; positions of the multiple atoms to be simulated are calculated at each time in a second time series in the scene by utilizing the improved GAN.Type: ApplicationFiled: November 26, 2019Publication date: June 4, 2020Applicant: FUJITSU LIMITEDInventors: Liuan WANG, Jun SUN
-
Publication number: 20200082275Abstract: Disclosed are a neural network architecture search apparatus and method and a computer readable recording medium. The neural network architecture search method comprises: defining a search space used as a set of architecture parameters describing the neural network architecture; performing sampling on the architecture parameters in the search space based on parameters of a control unit, to generate at least one sub-neural network architecture; performing training on each sub-neural network architecture by minimizing a loss function including an inter-class loss and a center loss; calculating a classification accuracy and a feature distribution score, and calculating a reward score of the sub-neural network architecture based on the classification accuracy and the feature distribution score; and feeding back the reward score to the control unit, and causing the parameters of the control unit to be adjusted towards a direction in which the reward scores are larger.Type: ApplicationFiled: August 23, 2019Publication date: March 12, 2020Applicant: FUJITSU LIMITEDInventors: Li SUN, Liuan WANG, Jun SUN
-
Publication number: 20190362236Abstract: A method and apparatus of accelerating deep learning, and a deep neural network are provided. The method comprises: randomly initializing weights and biases of a deep neural network as n-bit fixed-point numbers; reducing data in a plurality of layers in the deep neural network that have calculation amounts are greater than a first predetermined threshold as m-bit fixed-point numbers, where m and n are integers and m<n, and maintaining data in remaining layers among the plurality of layers as n-bit fixed-point numbers; and training the deep neural network after the reducing, until convergence.Type: ApplicationFiled: January 18, 2019Publication date: November 28, 2019Applicant: FUJITSU LIMITEDInventors: Liuan WANG, Jun SUN
-
Publication number: 20180189650Abstract: A device and a method for improving a processing speed of a neural network and applications thereof in the neural network where the device includes a processor configured to perform: determining, according to a predetermined processing speed improvement target, a dimension reduction amount of each of one or more parameter matrixes in the neural network obtained through training; preprocessing each parameter matrix based on the dimension reduction amount of the parameter matrix; and retraining the neural network based on a result of the preprocessing to obtain one or more dimension reduced parameter matrixes so as to ensure performance of the neural network meets a predetermined requirement. According to the embodiments of the present disclosure, it is possible to significantly improve the processing speed of the neural network while ensuring the performance of the neural network meets the predetermined requirement.Type: ApplicationFiled: October 31, 2017Publication date: July 5, 2018Applicant: FUJITSU LIMITEDInventors: Liuan WANG, Wei FAN, Jun SUN