当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improved covariant local feature detector
Pattern Recognition Letters ( IF 3.9 ) Pub Date : 2020-03-30 , DOI: 10.1016/j.patrec.2020.03.027
Zhanqiang Huo , Yanqi Zhang , Hongmin Liu , Jing Wang , Xin Liu , Jiyong Zhang

Local feature detection is a fundamental problem in computer vision. Recently, the research of local feature detection has been switched from handcrafted methods to learning based ones, especially deep learning based ones. A recent successful deep learning based feature detector is the covariant local feature detector that conducts keypoint detection by predicting the transformation of keypoints from nearby pixels. Although this method adopts a new detection framework compared to those methods by computing the keypoint’s likelihood, it treats each pixel equally which may incorrectly detect unstable keypoints. On the other hand, other methods computing the keypoint probability could capture different evidence for keypoint detection as well as provide a natural weight for each prediction in the covariant detector. So, fusing information from other detectors into the covariant detector could improve its performance. Under this motivation, this paper proposes an improved covariant local feature detector by fusing feature information obtained from another detector, which is served as a confidence to guide the voting procedure when converting the predicted transformations into a meaningful score map for keypoint detection. In this way, the fused information can enhance the features that are considered to be good and weaken those unstable features. The proposed method is evaluated on four widely used benchmarks and consistent performance improvement over previous works is observed.



中文翻译:

改进的协变局部特征检测器

局部特征检测是计算机视觉中的基本问题。最近,局部特征检测的研究已从手工方法转变为基于学习的方法,尤其是基于深度学习的方法。最近成功的基于深度学习的特征检测器是协变局部特征检测器,它通过预测来自附近像素的关键点的转换来进行关键点检测。尽管与通过计算关键点可能性的方法相比,该方法采用了一种新的检测框架,但它会同等对待每个像素,这可能会错误地检测到不稳定的关键点。另一方面,其他计算关键点概率的方法可以捕获关键点检测的不同证据,并为协变量检测器中的每个预测提供自然权重。所以,将其他检测器中的信息融合到协变检测器中可以改善其性能。在这种动机下,本文提出了一种改进的协方差局部特征检测器,它融合了从另一个检测器获得的特征信息,当将预测的变换转换为有意义的分数图以进行关键点检测时,该置信度可用来指导投票程序。这样,融合信息可以增强被认为是好的特征,并减弱那些不稳定的特征。在四个广泛使用的基准上对提出的方法进行了评估,并观察到与以前的工作相比性能持续提高。本文提出了一种改进的协变局部特征检测器,它融合了从另一个检测器获得的特征信息,当将预测的变换转换成有意义的分数图以进行关键点检测时,可以作为一种信心来指导投票程序。这样,融合信息可以增强被认为是好的特征,并减弱那些不稳定的特征。在四个广泛使用的基准上对提出的方法进行了评估,并观察到与以前的工作相比性能持续提高。本文提出了一种改进的协变局部特征检测器,它融合了从另一个检测器获得的特征信息,当将预测的变换转换成有意义的分数图以进行关键点检测时,可以作为一种信心来指导投票程序。这样,融合信息可以增强被认为是好的特征,并减弱那些不稳定的特征。在四个广泛使用的基准上对提出的方法进行了评估,并观察到与以前的工作相比性能持续提高。融合的信息可以增强被认为是好的特征,并减弱那些不稳定的特征。在四个广泛使用的基准上对提出的方法进行了评估,并观察到与以前的工作相比性能持续提高。融合的信息可以增强被认为是好的特征,并减弱那些不稳定的特征。在四个广泛使用的基准上对提出的方法进行了评估,并观察到与以前的工作相比性能持续提高。

更新日期:2020-03-30
down
wechat
bug