Kookmin University

Hoo Kyung Lee

Dong Sun Lim

Jin Woo Yoo

Jin Gwan Kim

Won Woo Lee

Yoon Suk Choi

An object detection method and apparatus are disclosed. The object detection method may include acquiring identification information of an object detected from each of N (N being a preset integer of 3 or more) images continuous in order of capture from the output of a classification layer of an object detection deep learning network and correcting, based on the identification information of the object detected from each of at least two images that have been captured early in order of time, among the N images, the identification information of the object detected from an image that has been captured later in order of time than the at least two images that have been captured early in order of time, among the N images.

Method and apparatus for detecting an object based on identification information of the object in continuous images

This application relates to a device and a method for calculating a fault ratio. The method may include by using image frames collected from a camera of a first vehicle, generating a driving route in which the first vehicle travels, and acquiring fault information of a traffic accident involving a second vehicle, the traffic accident being related to the driving route of the first vehicle. The method may also include changing factors related to braking or steering of the first vehicle and the second vehicle, and generating multiple simulation driving scenarios by simulating the driving route on the basis of the changed factors. The method may further include computing a fault ratio of the first vehicle and the second vehicle for each of the multiple simulation driving scenarios by correcting the fault information on the basis of the factors.

Growing community of inventors

Seoul, South Korea

Hoo Kyung Lee