本文選題：復(fù)雜背景 + 列車駕駛員目標(biāo)檢測(cè)��； 參考：《鄭州大學(xué)》2017年碩士論文

【摘要】：從列車監(jiān)控視頻中自動(dòng)、準(zhǔn)確、快速地檢測(cè)與定位列車駕駛員,已成為目前相關(guān)管理部門規(guī)范駕駛員操作行為,保證列車行駛安全的迫切需求。然而,在實(shí)際的監(jiān)控視頻中,由于圖像分辨率較低、實(shí)際背景復(fù)雜、人體姿態(tài)多變、遮擋以及截?cái)嗟那樾屋^多,使得列車駕駛員目標(biāo)檢測(cè)成為了計(jì)算機(jī)視覺領(lǐng)域極具挑戰(zhàn)性的研究課題。針對(duì)現(xiàn)有人體檢測(cè)算法直接應(yīng)用于列車駕駛員目標(biāo)檢測(cè)時(shí)所出現(xiàn)的問題,本文提出一種基于單張圖像的列車駕駛員目標(biāo)檢測(cè)方法。首先,該方法以傳統(tǒng)可變形部件模型為基礎(chǔ),分別提出單人檢測(cè)器、遮擋檢測(cè)器以及截?cái)鄼z測(cè)器,用以解決完整、遮擋、截?cái)囫{駛室場(chǎng)景下的人員檢測(cè)難題;其次,綜合三個(gè)檢測(cè)器各自的特性,提出聯(lián)合檢測(cè)器,實(shí)現(xiàn)復(fù)雜行車環(huán)境下的列車駕駛員目標(biāo)檢測(cè);最后,采用最優(yōu)部件子集策略和coarse-to-fine策略分別從精度和速度兩方面改進(jìn)聯(lián)合檢測(cè)器,使其在提高檢測(cè)精度的同時(shí),也充分保證檢測(cè)速度。聯(lián)合檢測(cè)器在基于單張圖像的列車駕駛員目標(biāo)檢測(cè)中取得了較好的結(jié)果,但是該檢測(cè)器并不能充分滿足視頻中的駕駛員目標(biāo)檢測(cè)需求,尤其是當(dāng)駕駛員的肢體處于運(yùn)動(dòng)(包含微動(dòng))狀態(tài)時(shí),由于視頻中的時(shí)空信息未被充分利用,在某些幀中往往會(huì)出現(xiàn)駕駛員誤檢及漏檢問題。針對(duì)該問題,本文以聯(lián)合檢測(cè)器為基礎(chǔ),提出C-STC框架實(shí)現(xiàn)監(jiān)控視頻中的列車駕駛員目標(biāo)檢測(cè)。該框架首先利用聯(lián)合檢測(cè)器獲取每幀圖像的初始駕駛員目標(biāo)檢測(cè)結(jié)果;然后,使用空間上下文約束對(duì)每幀的初始檢測(cè)結(jié)果進(jìn)行后處理,抑制部分誤檢發(fā)生;最后,基于時(shí)間上下文約束策略,提出最優(yōu)動(dòng)態(tài)調(diào)整閾值方法實(shí)現(xiàn)視頻中駕駛員的準(zhǔn)確檢測(cè)。實(shí)驗(yàn)結(jié)果表明,本文提出的聯(lián)合檢測(cè)器針對(duì)單張圖像實(shí)現(xiàn)了準(zhǔn)確、快速的列車駕駛員目標(biāo)檢測(cè)。在此基礎(chǔ)上,綜合聯(lián)合檢測(cè)器與時(shí)空約束策略的共同作用,使得本文所提出的C-STC框架針對(duì)監(jiān)控視頻的列車駕駛員目標(biāo)檢測(cè)取得了較好的檢測(cè)結(jié)果,并可應(yīng)用于實(shí)時(shí)系統(tǒng)中。
[Abstract]:Detecting and locating train drivers automatically, accurately and quickly from the video of train surveillance has become an urgent need for the relevant management departments to regulate the driver's operation behavior and ensure the safety of the train running. However, in the actual surveillance video, due to the low resolution of the image, the actual background is complex, the human body posture is changeable, occlusion and truncation are more, Train driver target detection has become a very challenging research topic in the field of computer vision. In order to solve the problem that the existing human body detection algorithm is directly applied to train driver target detection, this paper presents a method of train driver target detection based on single image. Firstly, based on the traditional deformable component model, the single detector, occlusion detector and truncation detector are proposed to solve the problem of personnel detection in the scene of complete, occluded and truncated cab. Based on the characteristics of the three detectors, a joint detector is proposed to detect the target of train driver in complex driving environment. Finally, the optimal component subset strategy and coarse-to-fine strategy are used to improve the accuracy and speed of the joint detector, respectively. So that it can improve the accuracy of the detection, but also fully ensure the detection speed. The joint detector has achieved good results in train driver target detection based on single image, but this detector can not fully meet the needs of driver target detection in video. Especially when the driver's limbs are in the state of motion (including fretting), because the space-time information in the video is not fully utilized, the problem of the driver's false detection and missed detection often occurs in some frames. In order to solve this problem, a C-STC framework is proposed to detect train driver targets in surveillance video based on joint detector. The framework firstly uses a joint detector to obtain the initial driver target detection results of each frame image; then, the spatial context constraints are used to post-process the initial detection results of each frame to suppress the occurrence of partial misinformation. Based on the temporal context constraint strategy, an optimal dynamic threshold adjustment method is proposed to detect drivers accurately in video. The experimental results show that the proposed joint detector realizes accurate and fast train driver target detection for a single image. On this basis, the combined action of joint detector and space-time constraint strategy makes the proposed C-STC framework obtain better detection results for train driver target detection in surveillance video, and it can be applied to real-time system.
【學(xué)位授予單位】：鄭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U29-39;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王武宏;駕駛員失誤機(jī)理辨識(shí)的可靠性靜態(tài)模型[J];中國(guó)公路學(xué)報(bào);1995年02期

2 連躍華;;駕駛員應(yīng)防止情緒波動(dòng)[J];汽車維護(hù)與修理;2000年02期

3 王榮本,郭克友,儲(chǔ)江偉,初秀民;適用駕駛員疲勞狀態(tài)監(jiān)測(cè)的人眼定位方法研究[J];公路交通科技;2003年05期

4 任有;許洪國(guó);李顯生;王維旭;許駿;;仿真追尾碰撞中駕駛員轉(zhuǎn)向反應(yīng)模型研究[J];交通運(yùn)輸系統(tǒng)工程與信息;2007年03期

5 馬艷;王令;郭華;;駕駛員交通心理劃分與個(gè)性化訓(xùn)練研究[J];公路交通科技(應(yīng)用技術(shù)版);2008年S1期

6 李金庫;;駕駛員綜合特征對(duì)行車控制與緊急度判斷的影響[J];交通科技與經(jīng)濟(jì);2008年03期

7 高菲;李向瑜;段立飛;王兵;;駕駛員前視行為特性的動(dòng)態(tài)變化規(guī)律[J];汽車工程師;2010年02期

8 張敬磊;王曉原;;駕駛員行為仿真模型研究進(jìn)展[J];山東理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年01期

9 馬愛靜;毛建國(guó);沈\，

本文編號(hào)：2113701