Mask R-CNN Algorithm Research Articles

Implementation of Modified Mask RCNN

Detecting camouflage moving object from the video sequence is the big challenge in computer vision. To detect moving object from dynamic background is also very difficult as the background is also detected as moving object. Mask RCNN is a deep neural network which solves the problem of separation of instances of same object in machine learning or computer vision. Thus, it separates different objects in video. It is the extension of faster RCNN in which an extra branch is added to create an object mask simultaneously along with bounding box and classifier. After giving input, Mask RCNN gives the rectangle around the object, class to which object belong and object mask. This article introduces Mask RCNN algorithm along with some modifications for target detection from dynamic background and also for camouflage handling. After target object detection, contrast limited adaptive histogram equalization is applied. Morphological operations are used to improve results. For both challenges quantitative and qualitative measures were obtained and compared with the existing algorithms. Our method efficiently detects the moving object from input sequence and gives best results in both situations.

이종 CNN 알고리즘을 이용한 물체 인식과 로봇의 파지 제어

The detection of robot manipulator’s object-grasping point is the most important step in precise handling of object. To grasp object needs some important parameters, which are object’s center coordinates (x, y, z) and width, yaw angle. In this paper, we predict not individual parameters but grasping area by using Segmentation Algorithm. Combining Mask R-CNN algorithm and Fully Convolutional Net algorithm and adding them to ROS, we construct ROS architecture. And, we apply them to control moving robot’s manipulator in grasping objects. So, we can reduce processing time for detecting object and improve applicability of this new method in robotic grasping control.

4.11 Rapid visuomotor processes drive the leg regardless of balance constraints

There is still ample room for further optimization of the application effect of virtual reality (VR) in smart products, and further expansion of the reconstruction research of smart home products. Hence, the related algorithms of spatial reconstruction and three-dimensional (3D) Computer-Aided Design (CAD) item reconstruction is proposed based on the relevant concepts of CAD and convolutional neural network. The algorithms aim to construct the virtual application scene and the simulation state of product usage by VR technology, and stimulate customers’ purchase decision. Through the experiments, it is found that the Fully Convolutional Network optimized by Visual Geometry Group Network can effectively realize scene reconstruction and item reconstruction. The average overall recognition accuracy of scene segmentation is 91.3%, and the mean Intersection over Union is 63.4%, showing a better recognition effect than other similar algorithms. Moreover, in the detection of indoor items, the maximum detection accuracy of the MaskR-CNN algorithm is 0.89, and the detection effect is also better than that of other algorithms. The experiments achieve a good spatial reconstruction structure, with the average voxel Prec rates in unsheltered space and sheltered space of 94.4% and 55.6%, and the average voxel Recall of 92.2% and 36.5%, respectively. The experimental results indicate an excellent spatial reconstruction effect. This study can provide a more scientific reference for subsequent VR system research.

AIDS testing and informed consent

The detection of deterioration in archeological heritage sites is a very time-consuming task that requires expertise. Furthermore, vision-based approaches can cause errors, considering the complex types of deterioration that develop in different scales and forms in monuments. This problem can be solved effectively owing to computer vision algorithms, commonly used in different areas nowadays. This study aims to develop a model that automatically detects and maps deteriorations (biological colonization, contour scaling, crack, higher plant, impact damage, microkarst, missing part) and restoration interventions using the Mask R-CNN algorithm, which has recently come to the fore with its feature of recognizing small and large-sized objects. To this end, a total of 2460 images of Yazılıkaya monuments in the Hattusa archeological site, which is on the UNESCO heritage list, were gathered. In the training phase of the proposed method, it was trained in model 1 to distinguish deposit deterioration commonly observed on the surface of monuments from other anomalies. Other anomalies trained were model 2. In this phase of the models, the average precision values with high accuracy rates ranging from 89.624% to 100% were obtained for the deterioration classes. The developed algorithms were tested on 4 different rock reliefs in Yazılıkaya, which were not used in the training phase. In addition, an image of the Eflatunpınar water monument, which is on the UNESCO tentative list, was used to test the model's universality. According to the test results, it was determined that the models could be successfully applied to obtain maps of deterioration and restoration interventions in monuments in different regions.