基于顏色屬性直方圖的尺度目標(biāo)跟蹤算法研究
doi: 10.11999/JEIT150921
-
1.
(空軍工程大學(xué)航空航天工程學(xué)院 西安 710038) ②(空軍工程大學(xué)空管領(lǐng)航學(xué)院 西安 710051)
國(guó)家自然科學(xué)基金(61472442, 61372167), 陜西省青年科技新星項(xiàng)目(2015KJXX-46)
Scale-adaptive Object Tracking Based on Color Names Histogram
-
1.
(Institute of Aeronautics and Astronautics Engineering, Air Force Engineering University, Xi&rsquo
-
2.
(Institute of ATC Navigation, Air Force Engineering University, Xi&rsquo
The National Natural Science Foundation of China (61472442, 61372167), The Young Star Science and Technology Program of Shaanxi (2015KJXX-46)
-
摘要: 利用目標(biāo)顏色信息的跟蹤算法,容易受到環(huán)境光照、尺度變化、相似背景等因素的干擾,導(dǎo)致跟蹤任務(wù)失敗。為了克服以上問(wèn)題,該文提出一種基于顏色屬性空間的魯棒尺度目標(biāo)跟蹤算法。該算法首先將原始的RGB顏色空間映射到顏色屬性(Color Names, CN)空間,減少目標(biāo)顏色在跟蹤過(guò)程中受環(huán)境變化影響。然后采用一種背景加權(quán)約束的顏色屬性直方圖,來(lái)抑制相似背景的干擾。最后,為了解決目標(biāo)尺度變化帶來(lái)的影響,先用梯度上升法粗略估計(jì)尺度,再用約束項(xiàng)精確求解尺度,并利用反向一致性檢驗(yàn),進(jìn)一步提高尺度估計(jì)的準(zhǔn)確性。該文選取了5段典型視頻進(jìn)行實(shí)驗(yàn),并與相關(guān)算法進(jìn)行比較。結(jié)果表明所提算法能夠消除環(huán)境光照、陰影、相似背景和尺度變化等因素所帶來(lái)的影響,在中心位置誤差和跟蹤成功率性能指標(biāo)上,優(yōu)于其它算法。
-
關(guān)鍵詞:
- 目標(biāo)跟蹤 /
- 顏色屬性 /
- 背景加權(quán)抑制 /
- 尺度自適應(yīng)
Abstract: Tracking effects of algorithms using color information are easily interfered by background clustering, illumination and scale changes, which can result in tracking failure. To solve these problems, an efficient model is proposed to project original RGB color space to a more robust color spaceColor Names (CN) feature space. Furthermore, objects are represented by background weighted color names histogram, and thus the similar background patches around the target are suppressed. Moreover, a two-step tuning way is adapted to estimate the scale by coarse tuning with gradient ascent and fine tuning with constrained items. Back-forward scale check is also used to ensure the precision of scale estimation. 5 representative videos are chosen to examine the proposed algorithms with four others. The results show that the proposed approach is robust to illumination variation, shadows, background clustering, and scale changes. The central distance error and tracking accuracy of the proposed approach also outperform the contrast algorithms.-
Key words:
- Object tracking /
- Color Names (CN) /
- Background weighted suppression /
- Scale-adaptive
-
POSSEGGER H, MAUTHNER T, and BISCHOF H. In defense of color-based model-free tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 2113-2120. ORON S, BAR-HILLEL A, LEVI D, et al. Locally orderless tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, USA, 2012: 1940-1947. 胡良梅, 段琳琳, 張旭東, 等. 融合顏色信息與深度信息的運(yùn)動(dòng)目標(biāo)檢測(cè)方法[J]. 電子與信息學(xué)報(bào), 2014, 36(9): 2047-2052. doi: 10.3724/SP.J.1146.2013.01763. HU Liangmei, DUAN Linlin, ZHANG Xudong, et al. Moving object detection based on the fusion of color and depth information[J]. Journal of Electronics Information Technology, 2014, 36(9): 2047-2052. doi: 10.3724/SP.J.1146. 2013.01763. MEER P, RAMESH V, and COMANICIU D. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-575. 張紅穎, 胡正. 融合局部三值數(shù)量和色度信息的均值漂移跟蹤[J]. 電子與信息學(xué)報(bào), 2014, 36(3): 624-630. doi: 10.3724/ SP.J.1146.2013.01155. ZHANG Hongying and HU Zheng. Mean shift tracking method combing local ternary number with hue information[J]. Journal of Electronics Information Technology, 2014, 36(3): 624-630. doi: 10.3724/SP.J.1146. 2013.01155. Van de WEIJER J, SCHMID C, and VERBEEK J. Learning color names from real-world Images[C]. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, USA, 2007: 1-8. Van de WEIJER J, SCHMID C, VERBEEK J, et al. Learning color names for real-world applications[J]. IEEE Transactions on Image Processing, 2009, 18(7): 1512-1523. KHAN F S, Van de WEIJER J, and VANRELL M. Modulating shape features by color attention for object recognition[J]. International Journal of Computer Vision, 2012, 98(1): 49-64. KHAN F S, ANWER R M, Van de WEIJER J, et al. Color attributes for object detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, USA, 2012: 3306-3313. DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive color attributes for real-time visual tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 1090-1097. COMANICIU D, RAMESH V, and MEER P. Real-time tracking of non-rigid objects using mean shift[C]. IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, USA, 2000: 142-149. NING J, ZHANG L, ZHANG D, et al. Scale and orientation adaptive mean shift tracking[J]. IET Computer Vision, 2012, 6(1): 52-61. VOJIR T, NOSKOVA J, and MATAS J. Robust scale- adaptive mean-shift for tracking[J]. Pattern Recognition Letters, 2014, 49(1): 250-258. WU Y, LIM J, and YANG M H. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition, Oregon, USA, 2013: 2411-2418. BOUGUET J Y. Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm[J]. Intel Corporation, 2001, 5(4): 1-10. -
計(jì)量
- 文章訪問(wèn)數(shù): 1556
- HTML全文瀏覽量: 203
- PDF下載量: 1651
- 被引次數(shù): 0