Encoding color information for visual tracking: Algorithms and benchmark

By Pengpeng Liang, Erik Blasch, Haibin Ling. IEEE Transactions on Image Processing, 2015

681 citations recorded by the source corpus.

While color information is known to provide rich discriminative clues for visual inference, most modern visual trackers limit themselves to the grayscale realm. Despite recent efforts to integrate color in tracking, there is a lack of comprehensive understanding of the role color information can play. In this paper, we attack this problem by conducting a systematic study from both the algorithm and benchmark perspectives. On the algorithm side, we comprehensively encode 10 chromatic models into 16 carefully selected state-of-the-art visual trackers. On the benchmark side, we compile a large set of 128 color sequences with ground truth and challenge factor annotations (e.g., occlusion). A thorough evaluation is conducted by running all the color-encoded trackers, together with two recently proposed color trackers. A further validation is conducted on an RGBD tracking benchmark. The results clearly show the benefit of encoding color information for tracking. We also perform detailed analysis on several issues, including the behavior of various combinations between color model and visual tracker, the degree of difficulty of each sequence for tracking, and how different challenge factors affect the tracking performance. We expect the study to provide the guidance, motivation, and benchmark for future work on encoding color in visual tracking.

Subfields: Computer Vision and Pattern Recognition, Social Psychology

View Paper: https://www.semanticscholar.org/paper/47b5e4d564f36bf322c14893b51ae4ecf782b53b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Social Psychology

Citations in the corpus

Context-Aware Correlation Filter Tracking (2017, background): “Large new datasets and benchmarks such as OTB-50 [26], OTB-100 [27], TC-128 [19], ALOV300++ [24] and UAV123 [23], as well as, tracking challenges such as the visual object tracking (VOT) challenge and multi-object tracking (MOT) challenge have sparked the interest of many researchers and helped adva”
Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications (2017, background): “There are several recent benchmarks that were created to address specific deficiencies of older benchmarks and introduce new evaluation approaches (Li et al. 2016; Liang et al. 2015; Smeulders et al. 2014), but they do not introduce videos with many tracking nuisances addressed in this paper and com”
Vision Meets Drones: A Challenge (2018, background): “[23] collect 128 video sequences for evaluating the color enhanced trackers.”
Fast Online Object Tracking and Segmentation: A Unifying Approach (2018, background): “This is the scenario portrayed by visual object tracking benchmarks, which represent the target object with a simple axisaligned [62, 34, 42, 59, 43] or rotated [30] bounding box.”
Learning Background-Aware Correlation Filters for Visual Tracking (2017, methodology): “We extensively evaluate our tracker on four standard datasets, including OTB50 [36], OTB100 [37], TempleColor128 (TC128) [23], and VOT2015 [18], comparing with 24 state-of-the-art methods, such as TLD [15], Struck [12], CFLB [17], KCF [13], DSST [7], SAMF [22], MEEM [38], DAT [29], LCT [27], HCF [26”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “[48], OTB2015 [186], TC128 [187], UAV123 [188], NUS-PRO [189], NfS [190], DTB [191], TrackingNet [192], OxUvA [193], BUAA-PRO [194], GOT10k [195], and LaSOT [196] are com-”
Target-Aware Deep Tracking (2019, methodology): “We evaluate the proposed tracker on ﬁve benchmark datasets including OTB-2013 [45], OTB-2015 [46], VOT-2015 [19, 20], VOT-2016 [18], and Temple Color-128 [24].”
LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking (2018, background): “Currently, the popular dense benchmarks contain OTB [52, 53], TC-128 [35], VOT [25], NUS-PRO [28], UAV [39], NfS [14] and GOT-10k [22].”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, methodology): “TC128 [37] comprises 129 videos, based on similar attributes and upright bounding boxes.”
The Visual Object Tracking VOT2016 Challenge Results (2016, methodology): “The OTB- and ALOV-related methodologies, like [21,22,24,25], evaluate a tracker by initializing it on the first frame and letting it run until the end of the sequence, while the VOT-related methodologies [16–20] reset the tracker once it drifts off the target.”
ECO: Efficient Convolution Operators for Tracking (2016, methodology): “We validate our proposed formulation by performing comprehensive experiments on four benchmarks: VOT2016 [23], UAV123 [29], OTB-2015 [37], and TempleColor [26].”
The Visual Object Tracking VOT2017 Challenge Results (2017, methodology): “Performance evaluation of short-term visual object trackers has received significant attention in the last five years [32, 33, 30, 31, 29, 68, 60, 77, 39, 40, 45, 41].”
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking (2018, methodology): “We perform comparative experiments on Temple-Color dataset [25] which consists of 128 color sequences.”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, methodology): “Our method is evaluated on three benchmark datasets: OTB-2013 [36], OTB-2015 [37], and Temple Color [22].”
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters (2019, methodology): “In this section, we demonstrate the effectiveness of our tracker on the OTB2015 [35], TC128 [27] VOT2016 [19], VOT2017 [20] and LaSOT [14] datasets.”
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (2016, methodology): “Success plots showing a comparison with state-of-the-art on the OTB-2015 (a) and Temple-Color (b) datasets.”