基于異構多核處理器的雙目視覺系統(tǒng)設計與實現(xiàn)
發(fā)布時間：2018-08-26 16:05
【摘要】：雙目視覺是計算機視覺領域的重要分支,其通過計算出同一場景下同一空間點在雙目圖像上的視差來恢復深度信息,這種深度信息恢復方式具有非接觸式和被動式兩大優(yōu)點。近年來,隨著對雙目匹配算法的深入研究,許多算法雖然在準確性上有了很大提高,但它們都以較理想的雙目圖像為前提。事實上由于現(xiàn)實成像因素的影響,常會導致雙目圖像在亮度等屬性上具有偏差,這就要求算法還應具備較高的魯棒性,另外,目前準確性較高的算法均具有計算量大、實時性差的特點,使其在要求實時處理的應用中很難運用。SGBM(Semi-global block matching)算法是一種半全局匹配算法,具有較高的準確性,但其魯棒性與實時性依然有待提高。因此本文對SGBM算法做了改進研究和并行加速方法研究,并將改進后的算法應用到本文雙目測距系統(tǒng)中。針對SGBM算法中BT匹配代價對亮度偏差不夠魯棒的問題,提出了一種聯(lián)合Census匹配代價的BT-Census匹配代價。由于Census匹配代價很好的保留了鄰域像素間的結構特性,因此在匹配時提高了對亮度偏差的魯棒性。為了提高實時性,本文對改進后的算法做了并行加速方法的研究,并基于OpenCL(Open Computing Language)異構并行計算框架做了實現(xiàn)。首先對該算法中匹配代價、代價優(yōu)化、視差計算及視差精細化模塊的主要算法做了并行化分析,然后在OpenCL框架下,對算法的數(shù)據(jù)存儲結構、OpenCL內核做了設計,并結合內核性能評估與算法優(yōu)化,實現(xiàn)了異構并行加速的算法。實驗表明,在同一處理器(AMD APU A8-4555M)上,本文算法在保證準確性相近的前提下,相比于經過SSE2指令集加速的SGBM算法,在實時性能上依然有2.2倍的提升。本文以上述改進的算法為核心,設計與實現(xiàn)了雙目測距系統(tǒng)。該雙目測距系統(tǒng),采用了基于異構多核處理器的計算平臺,不但減小了多核間的數(shù)據(jù)傳輸延遲,而且有效的控制了系統(tǒng)功耗。實驗表明,在雙目圖像尺寸為640×480,最大視差層級為64的條件下,該雙目測距系統(tǒng)平均測距周期為110ms,在0.5～5米以內的深度測量誤差小于9.6%,初步實現(xiàn)了一套低功耗、近實時的雙目測距系統(tǒng)。
[Abstract]:Binocular vision is an important branch in the field of computer vision. The depth information is restored by calculating the parallax of the same space point in the same scene on the binocular image. This depth information restoration method has two advantages: contactless and passive. In recent years, with the in-depth study of binocular matching algorithms, many algorithms have greatly improved in accuracy, but they are based on a more ideal binocular image as the premise. In fact, due to the influence of realistic imaging factors, binocular images often have deviations in luminance and other attributes, which requires that the algorithms should also have higher robustness. In addition, the current algorithms with high accuracy all have a large amount of computation. Because of the poor real-time performance, it is difficult to use SGBM (Semi-global block matching) algorithm, which is a semi-global matching algorithm, in the application of real-time processing, but its robustness and real-time performance still need to be improved. Therefore, the improved SGBM algorithm and the parallel acceleration method are studied in this paper, and the improved algorithm is applied to the binocular ranging system in this paper. Aiming at the problem that the BT matching cost is not robust to the brightness deviation in the SGBM algorithm, a new BT-Census matching cost combining the Census matching cost is proposed. Because the Census match cost is very good to retain the structure characteristics of the neighborhood pixels, so the robustness of the matching algorithm is improved to the luminance deviation. In order to improve real-time performance, the improved algorithm is studied by parallel acceleration method, and implemented based on OpenCL (Open Computing Language) heterogeneous parallel computing framework. Firstly, the main algorithms of matching cost, cost optimization, parallax calculation and parallax refinement module in this algorithm are analyzed in parallel. Then, the data storage structure of the algorithm is designed under OpenCL framework. Combined with kernel performance evaluation and algorithm optimization, heterogeneous parallel acceleration algorithm is realized. Experiments show that on the same processor (AMD APU A8-4555M), the proposed algorithm can improve the real-time performance by 2.2 times compared with the SGBM algorithm accelerated by the SSE2 instruction set, on the premise that the accuracy of the algorithm is similar. In this paper, the binocular ranging system is designed and implemented based on the improved algorithm. The binocular ranging system adopts a computing platform based on heterogeneous multi-core processor, which not only reduces the data transmission delay between multi-cores, but also effectively controls the power consumption of the system. The experimental results show that under the condition that the size of binocular image is 640 脳 480 and the maximum parallax level is 64, the average ranging period of the binocular ranging system is 110 Ms, and the depth measurement error within 0.5 m is less than 9. 6. A set of low power consumption is initially realized. Near-real-time binocular ranging system.
【學位授予單位】：北京交通大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
本文編號：2205431
[Abstract]:Binocular vision is an important branch in the field of computer vision. The depth information is restored by calculating the parallax of the same space point in the same scene on the binocular image. This depth information restoration method has two advantages: contactless and passive. In recent years, with the in-depth study of binocular matching algorithms, many algorithms have greatly improved in accuracy, but they are based on a more ideal binocular image as the premise. In fact, due to the influence of realistic imaging factors, binocular images often have deviations in luminance and other attributes, which requires that the algorithms should also have higher robustness. In addition, the current algorithms with high accuracy all have a large amount of computation. Because of the poor real-time performance, it is difficult to use SGBM (Semi-global block matching) algorithm, which is a semi-global matching algorithm, in the application of real-time processing, but its robustness and real-time performance still need to be improved. Therefore, the improved SGBM algorithm and the parallel acceleration method are studied in this paper, and the improved algorithm is applied to the binocular ranging system in this paper. Aiming at the problem that the BT matching cost is not robust to the brightness deviation in the SGBM algorithm, a new BT-Census matching cost combining the Census matching cost is proposed. Because the Census match cost is very good to retain the structure characteristics of the neighborhood pixels, so the robustness of the matching algorithm is improved to the luminance deviation. In order to improve real-time performance, the improved algorithm is studied by parallel acceleration method, and implemented based on OpenCL (Open Computing Language) heterogeneous parallel computing framework. Firstly, the main algorithms of matching cost, cost optimization, parallax calculation and parallax refinement module in this algorithm are analyzed in parallel. Then, the data storage structure of the algorithm is designed under OpenCL framework. Combined with kernel performance evaluation and algorithm optimization, heterogeneous parallel acceleration algorithm is realized. Experiments show that on the same processor (AMD APU A8-4555M), the proposed algorithm can improve the real-time performance by 2.2 times compared with the SGBM algorithm accelerated by the SSE2 instruction set, on the premise that the accuracy of the algorithm is similar. In this paper, the binocular ranging system is designed and implemented based on the improved algorithm. The binocular ranging system adopts a computing platform based on heterogeneous multi-core processor, which not only reduces the data transmission delay between multi-cores, but also effectively controls the power consumption of the system. The experimental results show that under the condition that the size of binocular image is 640 脳 480 and the maximum parallax level is 64, the average ranging period of the binocular ranging system is 110 Ms, and the depth measurement error within 0.5 m is less than 9. 6. A set of low power consumption is initially realized. Near-real-time binocular ranging system.
【學位授予單位】：北京交通大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
【參考文獻】
相關期刊論文 前5條
1 邸男;田睿;;空間機器人雙目視覺測量系統(tǒng)精度分析[J];載人航天;2017年01期
2 曹之樂;嚴中紅;王洪;;雙目立體視覺匹配技術綜述[J];重慶理工大學學報(自然科學);2015年02期
3 董峰;孫立寧;汝長海;;基于雙目視覺的醫(yī)療機器人擺位系統(tǒng)測量方法[J];光電子.激光;2014年05期
4 朱遵尚;苑云;李由;尚洋;于起峰;;嫦娥一號月面成像的高精度匹配及月貌三維重建[J];光學學報;2014年02期
5 于乃功;秦永鋼;阮曉鋼;;立體匹配算法進展[J];計算機測量與控制;2009年05期
，本文編號：2205431
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2205431.html
最近更新
教材專著
