Search

In visual-based localization, prior research falls short in addressing challenges for the Internet of Things with limited computational resources. The dominant state-of-the-art models are based on separate feature extractors and descriptors without consideration of the constraints of small hardware, the issue of inconsistent image scale, or the presence of multi-objects. We introduce “OOPose”, a real-time object-oriented pose estimation framework that leverages dense features from off-the-shelf object detection neural networks. It balances between pixel-matching accuracy and processing speed, enhancing overall performance. When input images share a comparable set of features, their matching accuracy is substantially heightened, while the reduction in image size facilitates faster processing but may compromise accuracy. OOPose resizes both the original library and cropped query object images to a width of 416 pixels. This adjustment results in a 2.4-fold improvement in pose accuracy and an 8.6-fold increase in processing speed. Moreover, OOPose eliminates the need for traditional sparse point extraction and description processes by capitalizing on dense network backbone features and selecting the detected query objects and sources of object library images, ensuring not only 1.3 times more accurate results but also three times greater stability compared to real-time sparse ORB matching algorithms. Beyond enhancements, we demonstrated the feasibility of OOPose in an autonomous mobile robot, enabling self-localization with a single camera at 10 FPS on a single CPU. It proves the cost-effectiveness and real-world applicability of OOPose for small embedded devices, setting the stage for potential markets and providing end-users with distinct advantages.

Localization is an important technology for smart services like autonomous surveillance, disinfection or delivery robots in future distributed indoor IoT applications. Visual-based localization (VBL) is a promising self-localization approach that identifies a robot’s location in an indoor or underground 3D space by using its camera to scan and match the robot’s surrounding objects and scenes. In this study, we present a pictorial planar surface based 3D object localization framework. We have designed two object detection methods for localization, ArPico and PicPose. ArPico detects and recognizes framed pictures by converting them into binary marker codes for matching with known codes in the library. It then uses the corner points on a picture’s border to identify the camera’s pose in the 3D space. PicPose detects the pictorial planar surface of an object in a camera view and produces the pose output by matching the feature points in the view with that in the original picture and producing the homography to map the object’s actual location in the 3D real world map. We have built an autonomous moving robot that can self-localize itself using its on-board camera and the PicPose technology. The experiment study shows that our localization methods are practical, have very good accuracy, and can be used for real time robot navigation.