https://github.com/qcraftai/simtrack GitHub - qcraftai/simtrack: Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021) Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021) - GitHub - qcraftai/simtrack: Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021) github.com 3D MOT 중 JDT(Joint Detection and Tracking) method를 사용한 논문의 코드..
1. Detection format [bboxes] [types] [velos] bboxes[scene][frame] : scene의 모든 frame에서 detected된 객체의 bbox 정보. 하나의 bbox는 다음과 같은 정보로 되어있다. ex) [238.55057929441963, 913.5869261780623, 0.8555841283783657, 1.8513201475143433, 4.525969505310059, 1.6440339088439941, -0.04874833532498536, -0.014557442911135306, -0.004948530062713921, -0.9986927418926963, 0.882607102394104] 순서대로 [translation(3), size(3), ..
evaluate.py에서 gt값을 불러오는 부분은 다음과 같다. gt_boxes = load_gt(nusc, self.eval_set, TrackingBox, verbose=verbose) load_gt()함수를 자세히 살펴보자. # Read out all sample_tokens in DB. sample_tokens_all = [s['token'] for s in nusc.sample] sample token을 sample.json에서 읽어옴. for sample_token in sample_tokens_all: scene_token = nusc.get('sample', sample_token)['scene_token'] scene_record = nusc.get('scene', scene_token)..
def main(): for object in objects(): #car, truck, pedestrian, ... for idx, file_name in enumerate(file_names): #데이터 한 세트 sequence_mot() -> ids, bboxes, states, types 저장 def sequence_mot(): for frame(): tracker.frame_mot() #tracking ids, bboxes, states, types.append() return ids, bboxes, states, types #모든 frame에 대한 정보가 들어있는 list 반환 class MOTmodel: def frame_mot(): for matched_track: #matched trac..
