SenseTime Group has been granted a patent for a method that predicts the direction of movement of a target object. The method involves acquiring the apparent orientation of the target object in an image captured by a camera device and determining the direction of movement based on the apparent orientation and the relative position relationship between the target object and the camera device in three-dimensional space. This technology can be used for smart vehicle control and other applications. GlobalData’s report on SenseTime Group gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on SenseTime Group, AI-assisted damage estimation was a key innovation area identified from patents. SenseTime Group's grant share as of September 2023 was 14%. Grant share is based on the ratio of number of grants to total number of patents.
Method for predicting motion orientation of a target object
A recently granted patent (Publication Number: US11710243B2) describes a computer-implemented method for predicting the motion orientation of a target object. The method involves acquiring the apparent orientation of the target object in an image captured by an imaging device and determining the motion orientation of the target object relative to the traveling direction of the imaging device. This information can be used to control the body where the imaging device is located or provide early warning prompting.
The method utilizes neural networks for apparent orientation detection and target object bounding box detection. The first neural network is trained with a training image set that includes labeling information of the apparent orientation of the target object. The neural network performs apparent orientation detection on sample image blocks to obtain the apparent orientation of the target object. Supervised learning is then performed on the neural network using the obtained apparent orientation and the labeling information as guidance.
The relative positional relationship between the target object and the imaging device in a three-dimensional space is determined by transforming the position of the target object in the image using a projection transformation matrix. The position of the imaging device in the three-dimensional space is also determined, and the included angle between a line connecting the positions and a normal of the motion orientation of the imaging device is calculated.
The patent also describes a computer-implemented intelligent vehicle control method that applies the same principles. The method acquires the apparent orientation of the target object and the relative positional relationship between the target object and the imaging device. It then determines the motion orientation of the target object relative to the traveling direction of the imaging device and generates instructions for controlling the vehicle or providing early warning prompting based on this information.
In summary, the granted patent outlines a computer-implemented method for predicting the motion orientation of a target object using apparent orientation detection and relative positional relationship determination. The method has applications in controlling the body where the imaging device is located or providing early warning prompting, particularly in the context of intelligent vehicle control.
To know more about GlobalData’s detailed insights on SenseTime Group, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
