-
公开(公告)号：US11972352B2
公开(公告)日：2024-04-30
申请号：US17980715
申请日：2022-11-04
发明人： Sima Taheri , Gang Qian , Sung Chun Lee , Sravanthi Bondugula , Allison Beach
IPC分类号： G06K9/00 , G06N3/084 , G06T7/254 , G06V10/20 , G06V10/764 , G06V10/778 , G06V10/82 , G06V10/98 , G06V40/20 , G06N5/046
CPC分类号： G06N3/084 , G06T7/254 , G06V10/255 , G06V10/764 , G06V10/7788 , G06V10/82 , G06V10/98 , G06V40/20 , G06V40/23 , G06N5/046 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/20224 , G06T2207/30196
摘要： Methods, systems, and apparatus for motion-based human video detection are disclosed. A method includes generating a representation of a difference between two frames of a video; providing, to an object detector, a particular frame of the two frames and the representation of the difference between two frames of the video; receiving an indication that the object detector detected an object in the particular frame; determining that detection of the object in the particular frame was a false positive detection; determining an amount of motion energy where the object was detected in the particular frame; and training the object detector based on penalization of the false positive detection in accordance with the amount of motion energy where the object was detected in the particular frame.
-
公开(公告)号：US11580833B2
公开(公告)日：2023-02-14
申请号：US17202528
申请日：2021-03-16
IPC分类号： G08B13/196 , H04N7/18 , H04N5/232
摘要： Methods, systems, and apparatus for camera detection of human activity with co-occurrence are disclosed. A method includes detecting a person in an image captured by a camera; in response to detecting the person in the image, determining optical flow in portions of a first set of images; determining that particular portions of the first set of images satisfy optical flow criteria; in response to determining that the particular portions of the first set of images satisfy optical flow criteria, classifying the particular portions of the first set of images as indicative of human activity; receiving a second set of images captured by the camera after the first set of images; and determining that the second set of images likely shows human activity based on analyzing portions of the second set of images that correspond to the particular portions of the first set of images classified as indicative of human activity.
-
公开(公告)号：US20210407107A1
公开(公告)日：2021-12-30
申请号：US17348047
申请日：2021-06-15
发明人： Sung Chun Lee , Gang Qian , Sima Taheri , Sravanthi Bondugula , Allison Beach
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for tracking moving objects depicted in multiple images. One of the methods includes determining, for an image captured by a camera, a first bounding box that represents a first moving object depicted in the image, determining that the first bounding box and a second bounding box overlap in an overlap area, determining that the first moving object represented by the first bounding box was farther from the camera that captured the image than a second moving object represented by the second bounding box, generating a mask for the first bounding box based on the overlap area, and determining, using data from the image that is associated with the mask, that the first moving object matches an appearance of another moving object depicted in another image captured by the camera.
-
公开(公告)号：US11210806B1
公开(公告)日：2021-12-28
申请号：US16546393
申请日：2019-08-21
发明人： Gang Qian , Yunxian Zhou , David Conger , Allison Beach
摘要： Methods and apparatus are disclosed for enhancing urban surface model with image data obtained from a satellite image. Three dimensional models of an urban cityscape obtained from digital surface models may comprise surface location information but lack image information associated with the cityscape, such as the color and texture of building facades. The location of the satellite at the time of recording the satellite image interest may be obtained from metadata associated with the satellite image. A 3D model of a cityscape corresponding to the satellite image may be subjected to a transformation operation to determine portions of the 3D model that are viewable from a location corresponding to the location of the satellite when taking the picture. Visible facades buildings of the 3D model ma be identified and mapped to portions of the satellite image which may then be used in rendering 2D images from the 3D model. In some examples a satellite image projection model may be adjusted to more accurately determine geolocations of portions of the satellite image by analysis of a plurality of satellite images.
-
公开(公告)号：US11200454B1
公开(公告)日：2021-12-14
申请号：US16655719
申请日：2019-10-17
发明人： Gang Qian , Allison Beach
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting people for a training set. The methods, systems, and apparatus include actions of: obtaining an image of a user, obtaining an initial training set that includes the image of the user as a positive example and images of a subset of a set of other people as negative examples, training an initial classifier with the images of the initial training set, determining false positive classifications by the initial classifier, selecting people in the set of other people based on the false positive classifications, obtaining an updated training set that includes an image of the user, images of the subset of the set of other people, and images of the people that are selected, and generating an updated classifier with the updated training set.
-
公开(公告)号：US20210365739A1
公开(公告)日：2021-11-25
申请号：US17319426
申请日：2021-05-13
发明人： Eduardo Romera Carmena , Gang Qian , Allison Beach
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for false detection removal using adversarial masks. The method includes performing object detection on a first image that includes a first region using a detection model determining the detection model incorrectly classified the first region of the first image; generating an adversarial mask based on the first region of the first image and the detection model; obtaining a second image that includes the first region; generating a masked image based on the second image and the adversarial mask; and performing object detection on the masked image including the first region using the detection model.
-
公开(公告)号：US11178363B1
公开(公告)日：2021-11-16
申请号：US16913604
申请日：2020-06-26
发明人： Gang Qian , Allison Beach , Donald Gerard Madden
IPC分类号： H04N7/18 , G08B13/196 , G06K9/00
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating distributed jobs for cameras in a monitored property. The methods, systems, and apparatus include actions of obtaining a request to process a video based on an event detected by a first camera at a monitored property, determining resources likely to be available corresponding to the other cameras at the monitored property, allocating one or more tasks corresponding to processing the video to the other cameras based on the resources likely to be available corresponding to the other cameras, and providing the one or more allocated tasks to the first camera and to the other cameras.
-
公开(公告)号：US12014271B2
公开(公告)日：2024-06-18
申请号：US18108282
申请日：2023-02-10
发明人： Sravanthi Bondugula , Gang Qian , Sung Chun Lee , Sima Taheri , Allison Beach
IPC分类号： G06N3/08 , G06F18/214 , G06T7/194 , G06V10/20 , G06V10/25 , G06V10/774 , G06V10/82
CPC分类号： G06N3/08 , G06F18/2148 , G06T7/194 , G06V10/25 , G06V10/255 , G06V10/7747 , G06V10/82
摘要： Methods, systems, an apparatus, including computer programs encoded on a storage device, for training an image classifier. A method includes receiving an image that includes a depiction of an object; generating a set of poorly localized bounding boxes; and generating a set of accurately localized bounding boxes. The method includes training, at a first learning rate and using the poorly localized bounding boxes, an object classifier to classify the object; and training, at a second learning rate that is lower than the first learning rate, and using the accurately localized bounding boxes, the object classifier to classify the object. The method includes receiving a second image that includes a depiction of an object; and providing, to the trained object classifier, the second image. The method includes receiving an indication that the object classifier classified the object in the second image; and performing one or more actions.
-
公开(公告)号：US11967139B2
公开(公告)日：2024-04-23
申请号：US17319426
申请日：2021-05-13
发明人： Eduardo Romera Carmena , Gang Qian , Allison Beach
IPC分类号： G06V10/82 , G06F18/21 , G06F18/214 , G06N3/04 , G06N3/08 , G06V10/764
CPC分类号： G06V10/82 , G06F18/214 , G06F18/217 , G06N3/04 , G06N3/08 , G06V10/764
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for false detection removal using adversarial masks. The method includes performing object detection on a first image that includes a first region using a detection model determining the detection model incorrectly classified the first region of the first image; generating an adversarial mask based on the first region of the first image and the detection model; obtaining a second image that includes the first region; generating a masked image based on the second image and the adversarial mask; and performing object detection on the masked image including the first region using the detection model.
-
公开(公告)号：US11935297B2
公开(公告)日：2024-03-19
申请号：US17476605
申请日：2021-09-16
发明人： Gang Qian , Allison Beach , Sima Taheri , Sravanthi Bondugula , Sung Chun Lee , Narayanan Ramanathan
CPC分类号： G06V20/41 , G06F18/214 , G06F18/22 , G06V10/225 , G06V10/25 , G06V20/46 , G06V20/48 , G06V20/52 , H04N7/18 , G06V20/44
摘要： Methods and systems, including computer programs encoded on a storage medium, are described for implementing item monitoring using a doorbell camera. A system generates an input video stream that has image frames corresponding to detection of activity at a property. Timing information is generated for the video stream and includes a timestamp for each image frame of the stream. Using the timing information, the system processes a pre-event image frame that precedes detection of the activity and a post-event image frame that coincides with detection of the activity. An image score is computed with respect to placement of a candidate item at the property in response to processing the pre-event and post-event image frames. The image score is used to determine that a first item was delivered to the property or that a second item was removed after being delivered to the property.
-
-
-
-
-
-
-
-
-
搜索结果
69 条记录 (耗时 0.022 秒)
