Kapsch TrafficCom has been granted a patent for a method of detecting wheels on a vehicle using a combination of 3D representation and 2D image recognition. The method involves directing a vehicle classification sensor and a camera onto a section of the road, recording a 3D representation and a 2D image, and using a projective transformation to detect the wheels on the vehicle. GlobalData’s report on Kapsch TrafficCom 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 Kapsch TrafficCom, Crowdsourced EV service mgmt was a key innovation area identified from patents. Kapsch TrafficCom's grant share as of September 2023 was 69%. Grant share is based on the ratio of number of grants to total number of patents.
Method for detecting vehicle wheels using 3d and 2d images
A recently granted patent (Publication Number: US11769331B2) describes a method for detecting wheels of a vehicle on a road using a combination of sensors, cameras, and image recognition processes. The method involves several steps to accurately identify and count the wheels of a vehicle.
The first step involves using a vehicle classification sensor and a camera to capture a 3D representation and a 2D image, respectively, of the vehicle passing a section of the road. A bounding box is then determined around the 3D representation, specifically on the side of the vehicle where the wheels are visible. The four corner points of this bounding box side are identified in the 2D image using a mapping technique.
Next, a projective transformation is calculated between the identified corner points in the 2D image and corresponding corner points in a destination 2D image plane. This transformation allows for the conversion of the source 2D image pixels to destination 2D image pixels. The wheels of the vehicle are then detected using an image recognition process applied to the transformed destination 2D image.
The patent also mentions additional features and variations of the method. For example, the bounding box side can be determined based on the proximity to the camera position or the direction of the vehicle's movement. The image recognition process can utilize a neural network trained on standardized images of vehicle wheels, and it can detect whether a wheel is raised from the road or if it is a double wheel. The method also allows for the counting of the detected wheels.
Furthermore, the patent describes the possibility of repeating the recording, determining, identifying, defining, calculating, and transforming steps for a second position of the vehicle or with a second camera. The resulting destination 2D images can be stitched together to create a stitched destination 2D image, which is then used for wheel detection.
Overall, this patented method provides a comprehensive approach to accurately detect and count the wheels of a vehicle on a road using sensors, cameras, and image recognition processes. The method's ability to handle different vehicle positions and camera angles enhances its versatility and applicability in various scenarios.
To know more about GlobalData’s detailed insights on Kapsch TrafficCom, 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.
