Vision-Based Hierarchical Recognition for Dismantling Robot Applied to Interior Renewal of Buildings

Abstract

New robotic systems are going to play an essential role in the future dismantling service for renewing office interiors in buildings. In dismantling tasks, robots are expected to be able to find and remove very small parts such as screws and bolts. Such recognition of small parts is difficult for robots. The article describes a vision-based hierarchical recognition applied to dismantling tasks where large structures are detected at first, thus small parts attached to these structures are detected easier. Regarding the items in the ceiling side, after the dismantling task of the ceiling panels, it is necessary to remove carefully the screws that once held these panels to the light gauge steel (LGS), with the purpose of reusing it. With the pose detection of the large structure (LGS) and considering a robot arm with a stereo camera on its tip, a trajectory near that structure can be computed to detect the small parts, in this case the screws. The large structure is detected by using a process of line detection in 2D and its 3D pose is measured with the stereo camera. During the motion along the structure, the screws are detected by applying a multi-template matching process to every captured image. Followed by, the Support Vector Machine (SVM), which recognizes those screw candidates with high true positive rate and low false positive one. These rates are improved with a temporal multi-image integration for tracking the screw candidates. In the experiment, 10 actual screws distributed in 1.1 m along a linear segment on the LGS are successfully recognized with a few false positives and with a final computed 3D position of 2 mm in average. Feasibility of methodology is evaluated by experimentation under different lighting conditions in a realistic environment. Experimental

Disassembly Automation

“…The plan for a new product is adapted from existing plans by deriving it from a base case. Gao et al [30] propose using a Fuzzy Reasoning Petri Net to adaptively generate the disassembly sequence according to the condition of the product observed at each state. Decisions are made based on the estimated value returned, hazard level, and disassembly cost.…”

“…Franke et al [30] state that the hybrid disassembly process is economically justified; the manual operation is essential due to the inability of automated systems to operate with a non-determined disassembly sequence and react to varying product conditions. The, manual operation is, therefore, the fallback option when the automatic operation has failed.…”

“…This is the method described in Elayed et al [4] to recognise components within a personal computer after "appropriate scaling, rotation and histogramequalization" following gross scene segmentation using a depth image. Following the localisation of ceiling beams using a Hough Transform, Rolando Cruz-Ramírez et al [30] generates a new trajectory for the acquisition of images, maintaining a fixed distance between camera and beam. Template matching is then used to generate hypotheses for the locations of screws.…”

“…In such contexts, it is common to first localise the product to be disassembled, then restrict the search space for smaller components to the area encompassing this product [4,30]. Jørgensen et al [41] uses a hierarchical tree model of products, whereby each node represents a component and the root nodes represent product classification.…”

Pedestrian detection in far infrared images

“…Image analysis and computer vision is lately being incorporated in civil engineering [13,28,47]. The applications are plenty and include freeway work zone analysis [1,27,36,37], automatic image search [34], human detection and modeling [12,69] and face recognition [7].…”