Search

Online multiple objects tracking (MOT) is a challenging problem due to occlusions and interactions among targets. An online MOT method with enhanced model updates and identity association is presented to handle the error drift and the identity switch problems in this work. The proposed MOT system consists of multiple single CNN(Convolutional Neural Networks)-based object trackers, where the shared CONV layers are fixed and used to extract the appearance representation while target-specific FC layers are updated online to distinguish the target from background. Two model updates are developed to build an accurate tracker. When a target is visible and with smooth movement, we perform the incremental update based on its recent appearance. When a target experiences error drifting due to occlusion, we conduct the refresh update to clear all previous memory of the target. Moreover, we introduce an enhanced online ID assignment scheme based on multi-level features to confirm the trajectory of each target. Experimental results demonstrate that the proposed online MOT method outperforms other existing online methods against the MOT17 and MOT16 benchmark datasets and achieves the best performance in terms of ID association.

Tracking-by-detection (TBD) is widely used in visual object tracking. However, many TBD-based methods ignore the strong motion correlation between current and previous frames. In this work, a motion-guided convolutional neural network (MGNet) solution to online object tracking is proposed. The MGNet tracker is built upon the multi-domain convolutional neural network with two innovations: (1) a motion-guided candidate selection (MCS) scheme based on a dynamic prediction model is proposed to accurately and efficiently generate the candidate regions and (2) the spatial RGB and temporal optical flow are combined as inputs and processed in an unified end-to-end trained network, rather than a two-branch processing network. We compare the performance of the MGNet, the MDNet and several state-of-the-art online object trackers on the OTB and the VOT benchmark datasets, and demonstrate that the temporal correlation between any two consecutive frames in videos can be more effectively captured by the MGNet via extensive performance evaluation.

A temporal prediction and spatial refinement (TPSR) method for online single object tracking (SOT) is proposed in this work. The TPSR tracking system consists of three cascaded modules: pre-processing (PP), temporal prediction (TP) and spatial refinement (SR). Illumination variation and shaking camera movement are two challenging factors in the tracking problem. They are first compensated in the PP module. Then, a joint region-based template matching (TM) and pixel-wised optical flow (OF) scheme is adopted in the TP module, where the switch between TM and OF is conducted automatically. These two modes work in a complementary manner to handle different foreground and background situations. Finally, to overcome the drifting error arising from the TP module, the bounding box location and size are finetuned using the local spatial information of the new frame in the SR module. The proposed TPSR tracking system offers the state-of-the-art performance with respect to a commonly used benchmarking dataset. HighlightsA robust tracker based on temporal prediction and spatial refinement is proposed.Temporal prediction relies on two complementary components.Fine-tuning using the local spatial information avoids the error drifting.

This paper presents a two-stage approach, track and then segment, to perform semi-supervised video object segmentation (VOS) with only bounding box annotations. The proposed reverse optimization for VOS (ROVOS) which leverages a fully convolutional Siamese network performs tracking and segmentation in the tracker. The segmentation cues are able to reversely optimize the location of the tracker and the object segmentation masks are produced by the two-branch system online. The experimental results on DAVIS 2016 and DAVIS 2017 demonstrate significant improvements of the proposed algorithm over the state-of-the-art methods.