帶權(quán)分塊壓縮感知的預(yù)測目標(biāo)跟蹤算法
doi: 10.11999/JEIT140997
基金項目:
國家973計劃項目(2010CB327900)，國家自然科學(xué)基金(61105042, 61462035)和江西省教育廳科技項目(GJJ13421)資助課題
Tracking Using Weighted Block Compressed Sensing and Location Prediction
-
摘要: 針對矩形跟蹤框在邊緣處包含較多背景信息的問題，該文提出一種基于規(guī)范化梯度特征的帶權(quán)分塊壓縮感知的目標(biāo)特征提取方法。該方法將壓縮感知測量矩陣轉(zhuǎn)化為分塊對角矩陣，且根據(jù)塊的重要程度分配適當(dāng)?shù)臋?quán)重，縮小測量矩陣規(guī)模，簡化特征提取運算，弱化背景干擾。然后將提取的特征輸入變先驗概率的貝葉斯分類器，變先驗概率的分類器充分利用已有的跟蹤結(jié)果，從一定程度預(yù)測了目標(biāo)的運動方向，減小候選目標(biāo)的分類歧義性，使得每一幀的分類函數(shù)根據(jù)以往跟蹤結(jié)果進行變化，提高了分類的準(zhǔn)確度。實驗在8個具有常見跟蹤難度的序列中測試，并與目前較流行的4種目標(biāo)跟蹤算法在跟蹤效果、成功率等方面進行比較，結(jié)果從多個角度表明，該文提出的目標(biāo)跟蹤算法具有較高的準(zhǔn)確度和穩(wěn)定性。
-
關(guān)鍵詞:
- 目標(biāo)跟蹤 /
- 分塊壓縮感知 /
- 貝葉斯分類器 /
- 變先驗概率
Abstract: To reduce side effects of background information included in the outer parts of tracking rectangular boxes, a weighted block compressed sensing feature extraction method is proposed based on normalized gradient features. The compressed sensing measurement matrix is converted to a block diagonal matrix. Appropriate weights are assigned to different blocks according to the importance of the blocks. It aims to reduce the measurement matrix size, weaken background interference and simplify feature extraction. Then the extracted features are inputted into Bayesian classifier with adaptive priori probabilities, which is proposed to make full use of existing tracking results. To some extent the classifier with variable priori probabilities can predict the direction of the moving targets, and reduce the ambiguities of target candidates. Each frame classification function changes according to the results of the previous track to improve the classification accuracy. In the experiments compared with four state-of-the-art tracking algorithms on 8 commonly used tracking test sequences, the proposed target tracking algorithm has higher accuracy and stability in terms of tracking results and success rate. -
計量
- 文章訪問數(shù): 1294
- HTML全文瀏覽量: 136
- PDF下載量: 990
- 被引次數(shù): 0
下載:
