Large Number Of Real Images Research Articles

Learning-Based Visual Servoing for High-Precision Peg-in-Hole Assembly

Visual servoing is widely used in the peg-in-hole assembly due to the uncertainty of pose. Humans can easily align the peg with the hole according to key visual points/edges. By imitating human behavior, we propose P2HNet, a learning-based neural network that can directly extract desired landmarks for visual servoing. To avoid collecting and annotating a large number of real images for training, we built a virtual assembly scene to generate many synthetic data for transfer learning. A multi-modal peg-in-hole strategy is then introduced to combine image-based search-and-force-based insertion. P2HNet-based visual servoing and spiral search are used to align the peg with the hole from coarse to fine. Force control is then used to complete the insertion. The strategy exploits the flexibility of neural networks and the stability of traditional methods. The effectiveness of the method was experimentally verified in the D-sub connector assembly with sub-millimeter clearance. The results show that the proposed method can achieve a higher success rate and efficiency than the baseline method in the high-precision peg-in-hole assembly.

Post-launch analysis, calibration, and validation of CCD line of sight for a space-borne push-broom electro-optical sensor using a global image data set

This article describes a technique which estimates line-of-sight (LOS) parameters of each CCD array in a high-resolution electro-optical sensor on board a satellite using statistical information which is extracted automatically from a large number of real images acquired after launch. First, the focal length of panchromatic (PAN) CCD arrays is estimated by using thousands of ground control points (GCPs) converted to raw image space. Second, a model is introduced for deriving LOS parameters for multispectral (MS) CCD arrays in one focal plane assembly (FPA) such as the focal lengths and the first/last detector cell positions from automatically matched band-to-band (B2B) tie-points. Finally, the LOS parameters of all arrays in one FPA are updated using automatically matched tie-points in the overlap zone (OZ) in order to represent the geometrical relationship between the CCD arrays with the same spectral band in two FPAs. The proposed technique was applied to the calibration of a ground segment image processor for a currently operating high-resolution imaging satellite during its initial commissioning phase. This article describes the accuracy and robustness of the LOS parameters estimated by the proposed technique by using more than one hundred images covering full geographical locations and off-nadir tilt angle ranges.

Design of Experiments for Performance Evaluation and Parameter Tuning of a Road Image Processing Chain

Tuning a complete image processing chain (IPC) is not a straightforward task. The first problem to overcome is the evaluation of the whole process. Until now researchers have focused on the evaluation of single algorithms based on a small number of test images and ad hoc tuning independent of input data. In this paper, we explain how the design of experiments applied on a large image database enables statistical modeling for IPC significant parameter identification. The second problem is then considered: how can we find the relevant tuning and continuously adapt image processing to input data? After the tuning of the IPC on a typical subset of the image database using numerical optimization, we develop an adaptive IPC based on a neural network working on input image descriptors. By testing this approach on an IPC dedicated-to-road obstacle detection, we demonstrate that this experimental methodology and software architecture can ensure continuous efficiency. The reason is simple: the IPC is globally optimized, from a large number of real images and with adaptive processing of input data.

Projection-based high accuracy measurement of straight line edges

We present a novel projection-based high accuracy algorithm to determine the parameters of a straight edge in a noisy image. Our algorithm is equivalent to applying a set of very long directional operators over a range of finely quantized angles. This is known to improve both signal-to-noise ratio and localization in the measurement of straight line edges, but was rarely used in practice because of the expense and coefficient restrictions of the operators. The algorithm is implemented by taking a set of projections of the original grey level image, filtering the projections, and analyzing the peaks in projection space to estimate line offset and angle. It also includes a procedure to analyze the peaks in projection space which provides an accuracy better than the quantization in offset and angle parameters. The algorithm was tested on synthetic and a large number of real images and offers very high (subpixel) offset and angular accuracy. The advantages of the algorithm over traditional approaches are improved signal-to-noise ratio and localization accuracy (due to the effective use of very long directional edge operators), no need for expensive edge operators and related hardware, and no need for sophisticated thresholding of the gradient image for finding edges. It is robust in the presence of many types of texture, patterned and bias noise, light intensity, and focus change, and is ideal for use in industrial machine vision, where a large number of parts with straight edges are processed.