基于自適應(yīng)深度稀疏網(wǎng)絡(luò)的在線跟蹤算法
doi: 10.11999/JEIT160762 cstr: 32379.14.JEIT160762
基金項(xiàng)目:
國家自然科學(xué)基金(61473309)；陜西省自然科學(xué)基礎(chǔ)研究計劃項(xiàng)目(2015JM6269, 2016JM6050)
Online Visual Tracking via Adaptive Deep Sparse Neural Network
Funds:
The National Natural Science Foundation of China (61473309), The Project Supported by Natural Science Basic Research Plan in Shaanxi Province (2015JM6269, 2016JM6050)
-
摘要: 視覺跟蹤中，高效魯棒的特征表達(dá)是解決復(fù)雜環(huán)境下跟蹤漂移問題的關(guān)鍵。該文針對深層網(wǎng)絡(luò)預(yù)訓(xùn)練復(fù)雜費(fèi)時及單網(wǎng)絡(luò)跟蹤易漂移的問題，在粒子濾波框架下，提出一種基于自適應(yīng)深度稀疏網(wǎng)絡(luò)的在線跟蹤算法。該算法利用ReLU激活函數(shù)，針對不同類型目標(biāo)構(gòu)建了一種具有自適應(yīng)選擇性的深度稀疏網(wǎng)絡(luò)結(jié)構(gòu)，僅通過有限標(biāo)簽樣本的在線訓(xùn)練，就可得到魯棒的跟蹤網(wǎng)絡(luò)。實(shí)驗(yàn)數(shù)據(jù)表明：與當(dāng)前主流的跟蹤算法相比，該算法的平均跟蹤成功率和精度均為最好，且與同樣基于深度學(xué)習(xí)的DLT算法相比分別提高了20.64%和17.72%。在光照變化、相似背景等復(fù)雜環(huán)境下，該算法表現(xiàn)出了良好的魯棒性，能夠有效地解決跟蹤漂移問題。
-
關(guān)鍵詞:
- 視覺跟蹤 /
- 在線訓(xùn)練 /
- 深度學(xué)習(xí) /
- 自適應(yīng)深度稀疏網(wǎng)絡(luò)
Abstract: In visual tracking, the efficient and robust feature representation is the key factor to solve the problem of tracking drift in complex environments. Therefore, to solve the problems of the complex and time-consuming of the pre-training process of deep neural network and the drift of the single network tracking, an online tracking method based on an adaptive deep sparse network is proposed under the tracking structure of particle filter. A deep sparse neural network architecture, which can be adaptively selected according to different types of targets, is constructed with the implementation of the Rectifier Linear Unit (ReLU) activation function. The robustness of deep tracking network can be easily achieved only through the online training of limited labeled samples. The results of experiments show that, compared with the state-of-the-art tracking algorithm, the average success ratio and precision of the proposed algorithm are both the highest, and they are raised by 20.64% and 17.72% respectively contrasted with the Deep Learning Tracker (DLT) algorithm based on deep learning. The proposed method can solve the problems of tracking drift efficiently, and shows better robustness, especially for the complex environment such as illumination changes, background clutter and so on.-
Key words:
- Visual tracking /
- Online training /
- Deep learning /
- Adaptive deep sparse network
-
SMEULDERS A W M, CHU D M, CUCCHIARA R, et al. Visual tracking: An experimental survey[J]. IEEE Transactions On Pattern Analysis and Machine Intelligence, 2014, 36(7): 1442-1468. doi: 10.1109/TPAMI.2013.230. WANG Naiyan, SHI Jianping, YEUNG Dityan, et al. Understanding and diagnosing visual tracking systems[C]. IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3101-3109. doi: 1109/ICCV.2015.355. ROSS D A, LIM J, LIN R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(1-3): 125-141. doi: 10.1007/s11263-007- 0075-7. BABENKO B, YANG M, and BELONGIE S. Robust object tracking with online multiple instance learning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632. doi: 10.1109/TPAMI.2010.226. KALAL Z, MIKOLAJCZYK K, and MATAS J. Tracking- learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422. doi: 10.1109/TPAMI.2011.239. ZHANG Kaihua, ZHANG Lei, and YANG Minghsuan. Real-time compressive tracking[C]. European Conference on Computer Vision, Florence, Italy, 2012: 864-877. WU Yi, LIM Jongwoo, and YANG Minghsuan. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013, 9(4): 2411-2418. doi: 10.1109/CVPR.2013.312. MA Chao, HUANG Jiabin, YANG Xiaokang, et al. Hierarchical convolutional features for visual tracking[C]. IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3074-3082. NAJAFABADI M M, VILLANUSTRE F, KHOSHGOFTAAR T M, et al. Deep learning applications and challenges in big data analytics[J]. Journal of Big Data, 2015, 2(1): 1-21. doi: 10.1186/s40537-014-0007-7. 李寰宇, 畢篤彥, 楊源, 等. 基于深度特征表達(dá)與學(xué)習(xí)的視覺跟蹤算法研究[J]. 電子與信息學(xué)報, 2015, 37(9): 2033-2039. doi: 10.11999/JEIT150031. LI Huanyu, BI Duyan, YANG Yuan, et al. Research on visual tracking algorithm based on deep feature expression and learning[J]. Journal of Electronics Information Technology, 2015, 37(9): 2033-2039. doi: 10.11999/JEIT150031. JIN J, DUNDAR A, BATES J, et al. Tracking with deep neural networks[C]. Annual Conference on Information Sciences and Systems, Baltimore, MD, USA, 2013: 213-217. WANG Naiyan and YEUNG Dityan. Learning a deep compact image representation for visual tracking[C]. Advances in Neural Information Processing Systems, South Lake Tahoe, Nevada, USA, 2013: 809-817. RUSSAKOVSKY O, DENG J, SU H, et al. Imagenet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252. doi: 10.1007/ s11263-015-0816-y. 侯志強(qiáng), 戴鉑, 胡丹, 等. 基于感知深度神經(jīng)網(wǎng)絡(luò)的視覺跟蹤[J]. 電子與信息學(xué)報, 2016, 38(7): 1616-1623. doi: 10.11999/ JEIT151449. HOU Zhiqiang, DAI Bo, HU Dan, et al. Robust visual tracking via perceptive deep neural network[J]. Journal of Electronics Information Technology, 2016, 38(7): 1616-1623. doi: 10.11999/JEIT151449. GLOROT X and BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[C]. International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 2010: 249-256. GLOROT X, BORDES A, and BENGIO Y. Deep sparse rectifier neural networks[C]. International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, 2011: 315-323. TOTH L. Phone recognition with deep sparse rectifier neural networks[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Vancounver, BC, Canada, 2013: 6985-6989. doi: 10.1109/ICASSP.2013.6639016. VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders: Iearning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11(6): 3371-3408. HE K, ZHANG X, REN S, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification[C]. IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1026-1034. WU Y W, ZHAO H H, and ZAHNG L Q. Image denoising with retified linear units[J]. Lecture Notes in Computer Science, 2014, 8836: 142-149. doi: 10.1007/978-3-319- 12643-2_18. LI X, HU W, SHEN C, et al. A survey of appearance models in visual object tracking[J]. ACM Transactions on Intelligent Systems and Technology, 2013, 4(4): 1-48. doi: 10.1145/ 2508037.2508039. WANG F S. Particle filters for visual tracking[C]. International Conference on Advanced Research on Computer Science and Information Engineering, Zhengzhou, China, 2011: 107-112. GRABNER H, GRABNER M, and BISCHOF H. Real-time tracking via on-line boosting[C]. British Machine Vision Conference, Edinburgh, Scotland, 2006: 47-56. ADAM A, RIVLIN E, and SHIMSHONI I. Robust fragments-based tracking using the integral histogram[C]. IEEE Conference on Computer Vision and Pattern Recognition, New York, USA, 2006: 798-805. -
計量
- 文章訪問數(shù): 1464
- HTML全文瀏覽量: 145
- PDF下載量: 299
- 被引次數(shù): 0
下載:
