-
291.
公开(公告)号:US20240242488A1
公开(公告)日:2024-07-18
申请号:US17915489
申请日:2021-10-28
Applicant: BOE Technology Group Co., Ltd.
Inventor: Zeyu SHANGGUAN , Zhanfu AN , Fanhao KONG
IPC: G06V10/776 , G06V10/25 , G06V10/44 , G06V10/82 , G06V20/70
CPC classification number: G06V10/776 , G06V10/25 , G06V10/44 , G06V10/82 , G06V20/70 , G06V2201/07
Abstract: Provided is a method for training a target detection model. The method includes: determining a first region in a sample image, wherein the first region is a target region predicted by the target detection model in the sample image; determining a relationship between an intersection region and the first region, wherein the intersection region is an intersection of the first region and a second region, wherein the second region is a region annotated for a target in the sample image in a data annotation phase, and surrounds the target in the sample image; determining, in response to the relationship between the intersection region and the first region satisfying a target relationship, a predetermined low loss function value as a loss function value of the first region, wherein the predetermined low loss function value is a constant; and training the target detection model with reference to the loss function value.
-
公开(公告)号:US20240242463A1
公开(公告)日:2024-07-18
申请号:US18414938
申请日:2024-01-17
Applicant: CANON KABUSHIKI KAISHA
Inventor: SOTA TORII
CPC classification number: G06V10/25 , G06V10/60 , G06V2201/07
Abstract: An information processing system using an individual separated compartment for detecting a target through use of the individual separated compartment, the information processing system including: an image acquisition unit configured to acquire an image including, as an object, a plurality of individual separated compartments in which a target is includable, an exclusion region determination unit configured to set, based on the image, a characteristic value for determining an exclusion region to be excluded from among a plurality of regions of the image, and determine the exclusion region based on the characteristic value of the plurality of regions, and a calculation unit configured to calculate information relating to the target from an image of individual separated compartments included in each region for calculation obtained by excluding the exclusion region from the image.
-
公开(公告)号:US20240242374A1
公开(公告)日:2024-07-18
申请号:US18617584
申请日:2024-03-26
Applicant: FUJIFILM Corporation
Inventor: Makoto YONAHA
CPC classification number: G06T7/70 , G06F3/14 , G06T7/0008 , G06T7/10 , G06V10/25 , G09G5/373 , G06T2207/30136 , G06V2201/07
Abstract: The information processing apparatus includes: a processor, in which the processor acquires an image, executes processing of region extraction to extract a region of a detection target from the image, generates position information of the region from region information of the extracted region, and displays a result of the processing of the region extraction by switching between a first display aspect in which information for informing of a position of the region is displayed on a display screen based on the position information in a visually appealing manner and a second display aspect in which the region information is displayed in an aspect different from the first display aspect according to at least one of a size of the extracted region or a display size of the region displayed on the display screen.
-
公开(公告)号:US12037018B2
公开(公告)日:2024-07-16
申请号:US17174689
申请日:2021-02-12
Applicant: Mobileye Vision Technologies Ltd.
Inventor: Shai Shalev-Shwartz , Shaked Shammah , Amnon Shashua , Barak Cohen , Zeev Adelman
IPC: B60W60/00 , B60W30/09 , B60W30/095 , B60W30/18 , B60W40/02 , B60W40/105 , B60W40/107 , G05D1/00 , G06T7/20 , G06T7/70 , G06V20/58 , G06V40/10
CPC classification number: B60W60/0016 , B60W30/09 , B60W30/0953 , B60W30/0956 , B60W30/181 , B60W30/18163 , B60W40/02 , B60W40/105 , B60W40/107 , B60W60/0015 , G05D1/0214 , G05D1/0231 , G05D1/0246 , G06T7/20 , G06T7/70 , G06V20/58 , G06V20/584 , G06V40/10 , B60W2420/42 , B60W2420/52 , B60W2510/18 , B60W2520/105 , B60W2520/12 , B60W2520/125 , B60W2520/14 , B60W2530/201 , B60W2552/45 , B60W2554/4029 , B60W2554/4041 , B60W2554/4042 , B60W2554/4043 , B60W2554/4044 , B60W2554/80 , B60W2554/801 , B60W2555/60 , B60W2720/10 , G05D2201/0213 , G06T2207/30196 , G06T2207/30261 , G06V2201/07
Abstract: Systems and methods are provided for navigating a host vehicle. At least one processing device may be programmed to receive an image of an environment of the host vehicle; detect, based on analysis of the image, a pedestrian crosswalk in the image; detect a presence of a traffic light and determine whether the traffic light is relevant to the host vehicle and the pedestrian crosswalk; determine a state of the traffic light; determine, when a pedestrian appears in the image, a proximity of the pedestrian relative to the pedestrian crosswalk; determine a planned navigational action for navigating the host vehicle relative to the pedestrian crosswalk based on a driving policy, the state of the traffic light and the proximity of the pedestrian relative to the pedestrian crosswalk; and cause one or more actuator systems of the host vehicle to implement the planned navigational action.
-
公开(公告)号:US20240233323A9
公开(公告)日:2024-07-11
申请号:US18382274
申请日:2023-10-20
Applicant: Fulhaus Inc.
Inventor: Dheeraj Reddy Peddireddy
IPC: G06V10/74
CPC classification number: G06V10/761 , G06V2201/07
Abstract: A computer-implemented method for selecting a furniture item based on a reference image, the method comprising: receiving a reference image and a room type; determining a main type of furniture items based on the room type; accessing a database comprising a plurality of main reference furniture items each belonging to the main type of furniture items; selecting a given one of the main reference furniture items based on the reference image; and outputting an identification of the given one of the main reference furniture items.
-
公开(公告)号:US20240233137A9
公开(公告)日:2024-07-11
申请号:US18275668
申请日:2022-02-11
Applicant: CALIPSA LIMITED
Inventor: SIDDHARTH AGRAWAL , ASHWIN D'CRUZ , CHRIS TEGHO , DAVID HALL , BORIS PLOIX
CPC classification number: G06T7/20 , G06T7/62 , G06V10/25 , G06V10/761 , G06V20/70 , G06V2201/07
Abstract: The present invention relates to identifying and/or generating high quality training data. More particularly, the present invention relates to determining a subset of images from a dataset that can be used as substantially high quality training data for the training of movement detection systems.
Aspects and/or embodiments seek to provide a system and/or method of generating substantially high quality training data for a security event detection method and/or system using video data from surveillance cameras as input data.-
公开(公告)号:US12035047B2
公开(公告)日:2024-07-09
申请号:US18083540
申请日:2022-12-18
Applicant: PAMTEK Co., Ltd.
Inventor: Jae Woong Kim , Jung In Park , Hyun Wook Shin , Kyung Sub Oh
CPC classification number: H04N23/695 , G01M11/0242 , G02B7/005 , G03B30/00 , G06V10/242 , G06V10/245 , G06V10/761 , H04N17/002 , H04N23/57 , G06V2201/07
Abstract: A camera module inspection system and a method for operating the inspection system. More specifically, the inspection system can quickly check and correct the alignment of the camera module.
-
公开(公告)号:US20240221392A1
公开(公告)日:2024-07-04
申请号:US18147531
申请日:2022-12-28
Applicant: Rivian IP Holdings, LLC
Inventor: Elaine Wenying Jin , Vidya Rajagopalan
CPC classification number: G06V20/588 , G02B5/3025 , G06V10/60 , G06V10/761 , H04N23/76 , G06V2201/07
Abstract: Systems and methods to enhance vehicle object detection capability are provided. The vehicle may include a first sensor coupled with a body of the vehicle, the first sensor having a first field of view and the first sensor comprising a polarizer. The vehicle may include a second sensor coupled with the body of the vehicle, the second sensor having a second field of view. The first field of view and the second field of view can at least partially overlap. The vehicle may include a processor coupled with memory. The processor can receive a first image captured by the first sensor and a second image captured by the second sensor. The processor can determine a luminance of light ratio associated with the first image and the second image, and can modify an image processing technique.
-
公开(公告)号:US20240221382A1
公开(公告)日:2024-07-04
申请号:US18558629
申请日:2022-05-04
Applicant: Verso Vision Oy
Inventor: Katja TAALAS , Lauri LAAKSONEN , Lauri FALOON , Toni KUPARINEN , Sinan KAPLAN
CPC classification number: G06V20/52 , G06T7/20 , G06V20/70 , G06V40/20 , G08B21/043 , G08B21/0476 , G06V2201/07
Abstract: A monitoring method of at least one person in a space includes receiving image data of the space, detecting at least one person from the image data, and determining the at least one detected person as a person to be monitored if it is detected from the image data that the at least one detected person fulfils at least one predetermined person to be monitored conditions. The present disclosure also relates to monitoring system for monitoring at least one person in a space and a computer program product performing the monitoring method.
-
公开(公告)号:US20240221361A1
公开(公告)日:2024-07-04
申请号:US18089663
申请日:2022-12-28
Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITED
Inventor: KeYong YU
IPC: G06V10/764 , G06V10/77 , G06V10/82
CPC classification number: G06V10/765 , G06V10/7715 , G06V10/82 , G06V2201/07
Abstract: Systems and methods for optimizing single shot detector (SSD) for object detection are disclosed herein. A system receives an image of a plurality of objects. Further, the system determines a plurality of feature layers and a plurality of feature cell sizes corresponding to the received image, based on an aspect ratio of the received image. Furthermore, the system determines aspect ratio of anchor boxes from trained model file, based on aspect ratio of anchor boxes, position and number of anchor boxes to be tiled in each feature cell of the plurality of feature layers. The size of the one or more anchor boxes corresponds to an anchor box aspect ratio. Additionally, the system assigns the one or more anchor boxes as a horizontal tile or a vertical tile in each feature cell, when the anchor box aspect ratio is less than a first pre-defined threshold value and greater than a second pre-defined threshold value, respectively. Further, the system generates one or more feature maps using an object detection model and a neural network (NN) model. The one or more feature maps comprises one or more feature map tensors. Furthermore, the system generates, for each layer of the one or more feature maps, a prediction tensor of predefined dimension from the one or more feature map tensors, using a prediction convolution layer. Additionally, the system detects and classifies the plurality of objects, based on the generated prediction tensor.
-
-
-
-
-
-
-
-
-