Recognition and distance estimation of an irregular object in package sorting line based on monocular vision

Abstract

In this article, we propose a monocular vision-based approach that can simultaneously recognize an object and estimate the distance to the target in package classification. Calibration is necessary due to lack of depth information in a single RGB image, and template matching makes it possible to estimate the distance of an irregular object without measurable parameters. First of all, capture images of the particular object as templates at set distances. Then, simplify the feature extraction to abandon the scale invariance. By exploiting a nonparametric estimation, the relationship between local feature correspondence and the similarity of two images is theoretically explored. Finally, the object will be recognized and the scale grade of it will be determined at the same time based on two-stage template matching. Experimental results have proved the high accuracy of our approach that has then been successfully applied to a real-time automatic package sorting line.

Object Position Estimation based on Dual Sight Perspective Configuration

“…Therefore, the right sensor to use is a vision sensor such as a camera. The vision sensor has various configurations available to use, such as mono or perspective vision [9], stereo vision [10], and omnidirectional vision [11], shown in Fig. 1, to detect objects.…”

Distance Estimation Methods for Smartphone-Based Navigation Support Systems

“…Some require object detection as a prerequisite to compute distance, while others compute distance based on information from specific sensors. Examples of such sensors include stereo cameras [40,41], monocular cameras [42,43], ultrasonic sensors [44,45], Light Detection and Ranging (LiDaR) [46], and Time of Flight (ToF) sensors [47].…”

Multi-Scale Dilated Convolution Network Based Depth Estimation in Intelligent Transportation Systems

“…(5) [4, 7, 11, 1], [19,29,37]. For dilation rates combinations, the dilation rates combination with [2, 5, 9, 1], [5,9,17] performs best.…”

“…This relationship is represented by the disparity d which is inverse to the depth value D: D = λ d , λ is a constant coefficient decided by the camera's parameters. Monocular depth prediction extracts the depth by scaling relative to the known size of familiar objects, exploiting the cues such as perspective, appearance in the form of lighting, shading and occlusion just as human eyes did [29].…”