Abstract
Object extraction is an important tool in many applications within the image processing and computer vision communities. You Only Look Once version 3 (YOLOv3) has been extensively applied to many fields as a state-of-the-art technique for object semantic detection. Despite its numerous characteristics, YOLOv3 has to be combined with appropriate image segmentation technologies to achieve effective 2D object extraction in real-time monitoring, robot navigation, and target search. In this article, the K-means algorithm is applied to the segmentation of depth images. Considering the inherent sensitivity to the randomness of the initial cluster center and the uncertainty of cluster number K in the initialization phase of the K-means algorithm, this article proposes a new method that combines the semantic image information with the image depth information. Specifically, this method proposed to pre-classify the center depth of the object to determine the appropriate value of K required in the K-means algorithm. At the same time, the proposed algorithm improves the selection of the initial center via the maximin method. This article introduces a multi-parameter extraction method to enable to correctly identify the object of interest after image segmentation. The technique considers three parameters to achieve this: i) the elements of size, ii) the connected domain, and iii) the diagonal detection. Experiments using open-source datasets demonstrate that the average processing time and the segmentation accuracy of the improved K-means algorithm are 20.36% faster and 3.12% higher than the conventional K-means algorithm, respectively. The extraction accuracy of the proposed method is 6.69% higher than that of the SuperCut extraction method.
Highlights
Object extraction aims to extract the Region of Interest (RoI) of a given image according to the detected position of an object of interest
The proposed method was compared with several popular methods, including one contour detection method and three unsupervised learning methods: SuperCut [12], Self-Organizing Maps (SOM) [13], Spectral method [14], Gaussian Mixture Model (GMM) method [15], and the variants of K-means
At the same time, compared with the results of the conventional K-means algorithm, the accuracy and speed of the proposed method are improved by 3.12% and 20.36%, respectively
Summary
Object extraction aims to extract the Region of Interest (RoI) of a given image according to the detected position of an object of interest. Despite the fact that object detection accuracy has been increased, the detection speed and the detection of objects with complex geometries needs to be improved. In such direction, Faster R-CNN [5], [6] has been developed giving rise to Mask R-CNN by adding the capability to predict segmentation masks on each Region of Interest (RoI) comprising the image. Faster R-CNN [5], [6] has been developed giving rise to Mask R-CNN by adding the capability to predict segmentation masks on each Region of Interest (RoI) comprising the image With such contributions, it is possible to perform
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have