Patents by Inventor Amir Sole
Amir Sole 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).
-
Patent number: 10438066Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: GrantFiled: June 29, 2018Date of Patent: October 8, 2019Assignee: Verint Americas Inc.Inventors: Gadi Zimerman, Itsik Horovitz, Shmuel Akerman, Amir Sole
-
Publication number: 20180307910Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: ApplicationFiled: June 29, 2018Publication date: October 25, 2018Applicant: Verint Americas Inc.Inventors: Gadi Zimerman, Itshak Horovitz, Shmuel Akerman, Amir Sole
-
Patent number: 10032080Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: GrantFiled: December 30, 2016Date of Patent: July 24, 2018Assignee: Verint Americas Inc.Inventors: Gadi Zimerman, Itsik Horovitz, Shmuel Akerman, Amir Sole
-
Patent number: 10032079Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: GrantFiled: February 19, 2016Date of Patent: July 24, 2018Assignee: Verint Americas Inc.Inventors: Gadi Zimerman, Itshak Horovitz, Shmuel Akerman, Amir Sole
-
Publication number: 20170109583Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: ApplicationFiled: December 30, 2016Publication date: April 20, 2017Applicant: Verint Americas Inc.Inventors: Gadi Zimerman, Itshak Horovitz, Shmuel Akerman, Amir Sole
-
Publication number: 20160275373Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: ApplicationFiled: February 19, 2016Publication date: September 22, 2016Inventors: Gadi Zimerman, Itsik Horovitz, Shmuel Akerman, Amir Sole
-
Patent number: 9268996Abstract: Models are generated from objects identified in video. Each model is evaluated based on knowledge of the objects determined from video analysis, and preferred models are identified based on the evaluations. In some examples, each model could be evaluated by tracking a movement of each object in the video by using each model to track the object from which it was generated, evaluating an ability of each model to identify the objects in the video that are similar to the object from which it was generated, and determining an amount of false identifications made by each model of different objects in different video that does not include the object from which it was generated.Type: GrantFiled: January 20, 2012Date of Patent: February 23, 2016Assignee: VERINT SYSTEMS INC.Inventors: Gadi Zimerman, Itshak Horovitz, Shmuel Akerman, Amir Sole
-
Patent number: 8879789Abstract: A method for object analysis using motion history is provided. The method includes receiving video data comprising a plurality of frames of a scene comprising one or more elements, and processing the video data to produce a motion history image comprising motion history values of at least one of the elements. The method also includes identifying the one of the elements for further processing if a characteristic of the motion history image satisfies a criteria.Type: GrantFiled: January 20, 2012Date of Patent: November 4, 2014Assignee: Verint Americas Inc.Inventors: Zvi Figov, Gadi Zimerman, Amir Sole
-
Patent number: 8379921Abstract: A video system for determining a region of interest in a video comprising a video source and a video processing system is provided. The video processing system is configured to receive the video from the video source and identify at least one object in the video which is in contact with the floor. The video processing system is further configured to determine a contact point between the object and the floor in a frame of the video and identify at least one polygon representing the floor in the frame, wherein the polygon includes the contact point. The video processing system is further configured to identify a three dimensional volume representing a space above the polygon extending to a designated height and select the region of interest by identifying a two dimensional area of the frame based on the three dimensional volume.Type: GrantFiled: January 26, 2011Date of Patent: February 19, 2013Assignee: Verint Systems Ltd.Inventors: Oren Golan, Shmuel Kiro, Itshak Horovitz, Amir Sole, Zvi Figov