Computer Vision – ECCV 2016 Workshops
Autor: | Songguo Jin, Enkhbayar Erdenee, Byungjae Lee, Phill Kyu Rhee |
---|---|
Rok vydání: | 2016 |
Předmět: |
Motion detector
business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Tracking (particle physics) Object (computer science) Convolutional neural network Class (biology) Video tracking Benchmark (computing) Point (geometry) Computer vision Artificial intelligence business |
Zdroj: | Lecture Notes in Computer Science ISBN: 9783319488806 |
DOI: | 10.1007/978-3-319-48881-3 |
Popis: | This paper presents a robust multi-class multi-object tracking (MCMOT) formulated by a Bayesian filtering framework. Multi-object 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. |
Databáze: | OpenAIRE |
Externí odkaz: |