Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (6): 1759-1762.DOI: 10.11772/j.issn.1001-9081.2017.06.1759

Previous Articles     Next Articles

Feature detection and description algorithm based on ORB-LATCH

LI Zhuo1, LIU Jieyu1, LI Hui2, ZHOU Xiaogang1, LI Weipeng1   

  1. 1. Institute of Control Engineering, Rocket Force University of Engineering, Xi'an Shaanxi 710025, China;
    2. Military Representative Office of the Rocket Force in the Fourth Research Institute, Xi'an Shaanxi 710025, China
  • Received:2016-11-23 Revised:2017-01-09 Online:2017-06-10 Published:2017-06-14
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61203007, 61304001).


李卓1, 刘洁瑜1, 李辉2, 周小刚1, 李维鹏1   

  1. 1. 火箭军工程大学 控制工程系, 西安 710025;
    2. 火箭军驻第四研究院军事代表室, 西安 710025
  • 通讯作者: 李卓
  • 作者简介:李卓(1992-),男,河北保定人,硕士研究生,主要研究方向:双目视觉导航、车辆定位定向;刘洁瑜(1970-),女,广东增城人,教授,博士,主要研究方向:惯性导航技术、精确制导技术;李辉(1978-),男,山西介休人,工程师,硕士,主要研究方向:导航制导与控制;周小刚(1979-),男,陕西西安人,讲师,博士,主要研究方向:精确制导与突防技术;李维鹏(1992-),男,湖北武汉人,硕士研究生,主要研究方向:移动机器人视觉同步定位与地图构建。
  • 基金资助:

Abstract: The binary descriptor based on Learned Arrangements of Three Patch Codes (LATCH) lacks of scale invariance and its rotation invariance depends upon feature detector, so a new feature detection and description algorithm was proposed based on Oriented fast and Rotated Binary robust independent elementary feature (ORB) and LATCH. Firstly, the Features from Accelerated Segment Test (FAST) was adopted to detect corner feature on the scale space of image pyramid. Then, the intensity centroid method of ORB was used to obtain orientation compensation. Finally, the LATCH was used to describe the feature. The experimental results indicate that, the proposed algorithm has the characteristics of low computational complexity, high real-time performance, rotation invariance and scale invariance. Under the same accuracy, the recall rate of the proposed algorithm is better than ORB and HARRIS-LATCH algorithm, the matching inner rate of the proposed algorithm is higher than ORB algorithm by 4.2 percentage points. In conclusion, the proposed algorithm can reduce the performance gap with histogram based algorithms such as Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Feature (SURF) while maintaining the real-time property, and it can deal with image sequence in real-time quickly and exactly.

Key words: feature detection, binary descriptor, scale invariance, rotation invariance, real-time property

摘要: 针对基于学习安排的三元组(LATCH)二进制描述子不具备尺度不变性且其旋转不变性,需要特征检测子辅助的问题,提出了一种基于快速定向旋转二进制稳健基元独立特征(ORB)和LATCH相结合的特征检测与描述算法。首先,在图像金字塔尺度空间上进行加速段测试特征(FAST)检测;然后,采用ORB灰度质心方法来进行方向补偿;最后,对特征进行LATCH描述。实验结果表明,所提算法具备运算量小、实时性高以及旋转和尺度不变性的特点,在相同的准确率下,其召回率优于ORB和哈里斯-LATCH (HARRIS-LATCH)算法,其匹配内点率比ORB算法提高了4.2个百分点。该算法在保持实时性的同时进一步缩小了与基于直方图的尺度不变特征变换(SIFT)和加速健壮特征(SURF)算法之间的精度差距,可对图像序列进行快速且精确的实时处理。

关键词: 特征检测, 二进制描述子, 尺度不变性, 旋转不变性, 实时性

CLC Number: