Multi-class Multi-object Tracking Using Changing Point Detection

Abstract

This paper presents a robust multi-class multi-object tracking (MCMOT) formulated by a Bayesian filtering framework. Multiobject tracking for unlimited object classes is conducted by combining detection responses and changing point detection (CPD) algorithm. The CPD model is used to observe abrupt or abnormal changes due to a drift and an occlusion based spatiotemporal characteristics of track states. The ensemble of convolutional neural network (CNN) based object detector and Lucas-Kanede Tracker (KLT) based motion detector is employed to compute the likelihoods of foreground regions as the detection responses of different object classes. Extensive experiments are performed using lately introduced challenging benchmark videos; ImageNet VID and MOT benchmark dataset. The comparison to state-of-the-art video tracking techniques shows very encouraging results.

Deformable ConvNets V2: More Deformable, Better Results

“…Note that the baseline accuracy is higher than that reported in [8] mainly because of a better ImageNet pretrained model and the introduction of RoIAlign in object detection. For object detection on Ima-geNet VID, we mainly follow the protocol in [27,43,42] for the training and inference settings. The details are presented at the end of this section.…”

Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds

“…First, an algorithm detects objects of interests and second, identical objects in different frames are associated. A widespread approach is using global information about the detections [17,7]. In contrast to this, online approaches don't have any knowledge of future frames.…”

Towards High Performance Video Object Detection

“…Experiments are performed on ImageNet VID [47], a large-scale benchmark for video object detection. Following the practice in [48,49], model training and evaluation are performed on the 3,862 training video snippets and the 555 validation video snippets, respectively. The snippets are at frame rates of 25 or 30 fps in general.…”

“…In training, following [48,49], both the ImageNet VID training set and the ImageNet DET training set are utilized. In each mini-batch of SGD, either n + 1 nearby video frames from ImageNet VID, or a single image from ImageNet DET, are sampled at 1:1 ratio.…”