Abstract: A method of sensing a three-dimensional (3D) space using at least one sensor is proposed. The method can include acquiring spatial information over time for the sensed 3D space, applying a neural network based object classification model to the acquired spatial information over time to identify at least one object in the sensed 3D space. The method can also include tracking the sensed 3D space including the identified at least one object, and using information related to the tracked 3D space.

Abstract: A collision accident prevention method, apparatus, server, and computer program are proposed. The method can include predicting, based on data on a three-dimensional (3D) space corresponding to a caution zone, motion of each of at least one pedestrian in the caution zone and at least one vehicle in the caution zone. The method may also include determining, based on the predicted motion, a degree of risk of collision between the at least one pedestrian and the at least one vehicle. The method may further include providing a message corresponding to the determined degree of risk of collision to the at least one vehicle.

Abstract: A method of sensing a three-dimensional (3D) space using at least one sensor is proposed. The method can include acquiring spatial information over time for the sensed 3D space, applying a neural network based object classification model to the acquired spatial information over time to identify at least one object in the sensed 3D space. The method can also include tracking the sensed 3D space including the identified at least one object, and using information related to the tracked 3D space.

Abstract: Provided is a method of sensing a three-dimensional (3D) space using at least one sensor. The method can include acquiring spatial information over time for the sensed 3D space, applying a neural network based object classification model to the acquired spatial information over time to identify at least one object in the sensed 3D space. The method can also include tracking the sensed 3D space including the identified at least one object, and using information related to the tracked 3D space.

Abstract: This application relates to a vehicle and method for generating a map corresponding to a three-dimensional space. In one aspect, the vehicle includes a sensor unit configured to sense a three-dimensional space by using at least one sensor and output spatial information in a plurality of frames and a memory storing computer executable instructions. The vehicle may also include a processor configured to execute the computer-executable instructions to predict a position of an object corresponding to a current frame by using an object movement model based on the plurality of frames, remove the object from the current frame based on the predicted position of the object, update a map database, which includes a predetermined number of previous frames, with the current frame from which the object is removed, and generate a map corresponding to the three-dimensional space based on the updated map database.

Abstract: Provided is a method of sensing a three-dimensional (3D) space using at least one sensor. The method can include acquiring spatial information over time for the sensed 3D space, applying a neural network based object classification model to the acquired spatial information over time to identify at least one object in the sensed 3D space. The method can also include tracking the sensed 3D space including the identified at least one object, and using information related to the tracked 3D space.