公开(公告)号：US20240233387A1

公开(公告)日：2024-07-11

申请号：US18612058

申请日：2024-03-21

Applicant: NVIDIA Corporation

Inventor： Parthasarathy Sriram ,  Ratnesh Kumar ,  Farzin Aghdasi ,  Arman Toorians ,  Milind Naphade ,  Sujit Biswas ,  Vinay Kolar ,  Bhanu Pisupati ,  Aaron Bartholomew

IPC: G06V20/54 ,  G06F18/231 ,  G06F18/2413 ,  G06T7/246 ,  G06T7/292 ,  G06T7/70 ,  G06T7/73 ,  G06V10/147 ,  G06V10/20 ,  G06V10/25 ,  G06V10/762 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V20/58 ,  G06V20/62 ,  G06V40/20 ,  H04N23/90

CPC classification number: G06V20/54 ,  G06F18/231 ,  G06F18/24143 ,  G06T7/246 ,  G06T7/292 ,  G06T7/70 ,  G06T7/73 ,  G06V10/147 ,  G06V10/25 ,  G06V10/255 ,  G06V10/7625 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V20/584 ,  G06V40/20 ,  H04N23/90 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30201 ,  G06T2207/30232 ,  G06T2207/30241 ,  G06T2207/30264 ,  G06V20/625 ,  G06V2201/08

Abstract: The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

公开(公告)号：US11941887B2

公开(公告)日：2024-03-26

申请号：US17943489

申请日：2022-09-13

Applicant: NVIDIA Corporation

Inventor： Parthasarathy Sriram ,  Ratnesh Kumar ,  Farzin Aghdasi ,  Arman Toorians ,  Milind Naphade ,  Sujit Biswas ,  Vinay Kolar ,  Bhanu Pisupati ,  Aaron Bartholomew

IPC: G06V40/20 ,  G06F18/231 ,  G06F18/2413 ,  G06T7/246 ,  G06T7/292 ,  G06T7/70 ,  G06T7/73 ,  G06V10/147 ,  G06V10/20 ,  G06V10/25 ,  G06V10/762 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V20/54 ,  G06V20/58 ,  H04N5/247 ,  H04N23/90 ,  G06V20/62

CPC classification number: G06V20/54 ,  G06F18/231 ,  G06F18/24143 ,  G06T7/246 ,  G06T7/292 ,  G06T7/70 ,  G06T7/73 ,  G06V10/147 ,  G06V10/25 ,  G06V10/255 ,  G06V10/7625 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V20/584 ,  G06V40/20 ,  H04N23/90 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30201 ,  G06T2207/30232 ,  G06T2207/30241 ,  G06T2207/30264 ,  G06V20/625 ,  G06V2201/08

Abstract: The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

公开(公告)号：US20230016568A1

公开(公告)日：2023-01-19

申请号：US17943489

申请日：2022-09-13

Applicant: NVIDIA Corporation

Inventor： Parthasarathy Sriram ,  Ratnesh Kumar ,  Farzin Aghdasi ,  Arman Toorians ,  Milind Naphade ,  Sujit Biswas ,  Vinay Kolar ,  Bhanu Pisupati ,  Aaron Bartholomew

IPC: G06V40/20 ,  G06T7/70 ,  H04N5/247 ,  G06T7/246 ,  G06V10/147 ,  G06V20/52 ,  G06V10/20 ,  G06T7/292 ,  G06T7/73 ,  G06K9/62 ,  G06V20/58 ,  G06V20/54 ,  G06V20/62

Abstract: The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

公开(公告)号：US11501572B2

公开(公告)日：2022-11-15

申请号：US16363869

申请日：2019-03-25

Applicant: NVIDIA Corporation

Inventor： Milind Naphade ,  Shuo Wang

IPC: G06V40/20 ,  G06V20/52 ,  G06V20/54 ,  G06V20/58 ,  G06V20/62 ,  G06T7/246 ,  G06T7/73 ,  G06T7/292 ,  G06T7/70 ,  H04N5/247 ,  G06K9/62 ,  G06V10/147 ,  G06V10/20

Abstract: In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

公开(公告)号：US11683453B2

公开(公告)日：2023-06-20

申请号：US16991770

申请日：2020-08-12

Applicant: NVIDIA Corporation

Inventor： Milind Naphade ,  Parthasarathy Sriram ,  Farzin Aghdasi ,  Shuo Wang

IPC: H04N7/18 ,  G11B27/30 ,  G11B27/34 ,  G06V20/40

CPC classification number: H04N7/183 ,  G06V20/46 ,  G11B27/3081 ,  G11B27/34 ,  G06V2201/10

Abstract: In various examples, cloud computing systems may store frames of video streams and metadata generated from the frames in separate data stores, with each type of data being indexed using shared timestamps. Thus, the frames of a video stream may be stored and/or processed and corresponding metadata of the frames may be stored and/or generated across any number of devices of the cloud computing system (e.g., edge and/or core devices) while being linked by the timestamps. A client device may provide a request or query to dynamically annotate the video stream using a particular subset of the metadata. In processing the request or query, the timestamps may be used to retrieve video data representing frames of the video stream and metadata extracted from those frames across the data stores. The retrieved metadata and video data may be used to annotate the frames for display on the client device.

公开(公告)号：US20230036879A1

公开(公告)日：2023-02-02

申请号：US17964716

申请日：2022-10-12

Applicant: NVIDIA Corporation

Inventor： Milind Naphade ,  Shuo Wang

IPC: G06V40/20 ,  G06T7/246 ,  G06T7/73 ,  G06T7/292 ,  G06T7/70 ,  H04N5/247 ,  G06K9/62 ,  G06V10/147 ,  G06V10/20 ,  G06V20/52 ,  G06V20/54 ,  G06V20/58

Abstract: In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

公开(公告)号：US20210348938A1

公开(公告)日：2021-11-11

申请号：US17307688

申请日：2021-05-04

Applicant: Nvidia Corporation

Inventor： Evan McLaughlin ,  Farzin Aghdasi ,  Milind Naphade ,  Arihant Jain ,  Sujit Biswas ,  Parthasarathy Sriram

IPC: G01C21/36 ,  G01C21/34 ,  G06K9/00

Abstract: Calibration of various sensors may be difficult without specialized software to process intrinsic and extrinsic information about the sensors. Certain types of input files, such as image files, may also lack certain information, like depth information, to effectively translate regions of interest between images taken from a different perspective. Landmarks can be used to establish points for associating regions of interest between images taken from a different perspective and provided as an overlay to verify sensor calibration.

公开(公告)号：US20190294869A1

公开(公告)日：2019-09-26

申请号：US16363869

申请日：2019-03-25

Applicant: NVIDIA Corporation

Inventor： Milind Naphade ,  Shuo Wang

IPC: G06K9/00 ,  G06T7/246 ,  G06T7/73

Abstract: In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

公开(公告)号：US11443555B2

公开(公告)日：2022-09-13

申请号：US16896431

申请日：2020-06-09

Applicant: NVIDIA Corporation

Inventor： Parthasarathy Sriram ,  Ratnesh Kumar ,  Farzin Aghdasi ,  Arman Toorians ,  Milind Naphade ,  Sujit Biswas ,  Vinay Kolar ,  Bhanu Pisupati ,  Aaron Bartholomew

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/20 ,  G06K9/32 ,  G06T7/73 ,  G06T7/70 ,  G06V40/20 ,  G06T7/246 ,  G06T7/292 ,  H04N5/247 ,  G06V10/147 ,  G06V10/20 ,  G06V20/52 ,  G06V20/54 ,  G06V20/58 ,  G06V20/62

Abstract: The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

公开(公告)号：US20200175392A1

公开(公告)日：2020-06-04

申请号：US16205876

申请日：2018-11-30

Applicant: NVIDIA Corporation

Inventor： Shuai Tang ,  Milind Naphade ,  Murali M. Gopalakrishna

IPC: G06N5/04 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08

Abstract: Apparatuses, methods, and computer program products are provided for inferring one or more paths of one or more objects, where each one or more objects corresponds to one or more different machine learning models. The inferred one or more paths of the one or more objects are further used to infer a path of a target object. Further, this is accomplished using a different machine learning model than the one or more different machine learning models.