17946343. VEHICLE CAMERA-BASED PREDICTION OF CHANGE IN PEDESTRIAN MOTION simplified abstract (GM GLOBAL TECHNOLOGY OPERATIONS LLC)

VEHICLE CAMERA-BASED PREDICTION OF CHANGE IN PEDESTRIAN MOTION

Organization Name

GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor(s)

Oded Bialer of Petach Tikva (IL)

Siddhartha Gupta of Rochester Hills MI (US)

VEHICLE CAMERA-BASED PREDICTION OF CHANGE IN PEDESTRIAN MOTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17946343 titled 'VEHICLE CAMERA-BASED PREDICTION OF CHANGE IN PEDESTRIAN MOTION

Simplified Explanation

The system in a vehicle described in the abstract includes a camera to capture video of pedestrians in the field of view, a controller to process the video and identify pedestrians, and a neural network to classify the motion of each pedestrian and predict their trajectory for the vehicle to adjust its operation accordingly.

• The system uses a camera to capture video of pedestrians in the vicinity of the vehicle.
• A controller processes the video to identify and track the motion of pedestrians.
• A neural network classifies the motion of each pedestrian into different categories, such as initiation of motion or no change in motion.
• Based on the classification of pedestrian motion, the system predicts the trajectory of each pedestrian.
• The vehicle adjusts its operation based on the predicted trajectories of pedestrians to ensure safety.

Potential Applications

This technology can be applied in autonomous vehicles, advanced driver-assistance systems (ADAS), and pedestrian detection systems in vehicles.

Problems Solved

1. Enhances pedestrian detection and tracking capabilities in vehicles. 2. Improves safety by predicting pedestrian trajectories and adjusting vehicle operation accordingly.

Benefits

1. Increased safety for pedestrians and drivers. 2. Enhanced efficiency in vehicle operation. 3. Improved accuracy in pedestrian detection and tracking.

Potential Commercial Applications

Optimizing pedestrian detection systems for autonomous vehicles and ADAS can lead to safer transportation systems and increased market demand for advanced safety features in vehicles.

Possible Prior Art

One possible prior art could be the use of computer vision and machine learning algorithms in pedestrian detection systems in vehicles. Another could be the integration of sensors and cameras for pedestrian tracking in autonomous vehicles.

Unanswered Questions

How does the system handle complex pedestrian behaviors, such as sudden changes in direction or speed?

The system may need to continuously update its predictions based on real-time data to adapt to sudden changes in pedestrian behavior.

What are the limitations of the system in different environmental conditions, such as low light or adverse weather?

The system may face challenges in accurately detecting and tracking pedestrians in poor visibility conditions, which could impact its overall effectiveness and safety.

Original Abstract Submitted

A system in a vehicle includes a camera to obtain video in a field of view over a number of frames and a controller to process the video to identify one or more pedestrians. The controller also implements a neural network to provide a classification of a motion of each pedestrian among a set of classifications of pedestrian motion. Each classification among the set of classifications indicates initiation of the motion or no change in the motion. The controller predicts a trajectory for each pedestrian based on the classification of the motion, and controls operation of the vehicle based on the trajectory predicted for each pedestrian.