Beyond ICONDENSATION: AICONDENSATION and AFCONDENSATION for visual tracking with low-level and high-level cues

Abstract

The paper presents a probabilistic tracking framework to fuse high-level object detection cues with low-level image feature cues using particle filters. First, an adaptive ICONDENSATION (AICONDENSATION) is introduced to better exploit object detection cues to guide importance sampling, where the proposal distribution is derived in a more principled approach using data association methods so that mixture weights can be adapted dynamically rather than fixed in ICONDENSATION. An adaptive detection fusion CONDENSATION (AFCONDENSATION) is further presented to directly fuse high-level object detection cues with low-level cues, where mixture weights are also adapted and it is shown that weight correction in ICONDENSATION actually is not necessary. Results on sequences with both simulated and real detections show improved performance of AI/AFCONDENSATION in comparison with ICONDENSATION.