Hidenori Takauji

Object detection based on a robust and accurate statistical multi-point-pair model

In this paper, we propose a robust and accurate background model, called grayscale arranging pairs (GAP). The model is based on the statistical reach feature (SRF), which is defined as a set of statistical pair-wise features. Using the GAP model, moving objects are successfully detected under a variety of complex environmental conditions. The main concept of the proposed method is the use of multiple point pairs that exhibit a stable statistical intensity relationship as a background model. The intensity difference between pixels of the pair is much more stable than the intensity of a single pixel, especially in varying environments. Our proposed method focuses more on the history of global spatial correlations between pixels than on the history of any given pixel or local spatial correlations. Furthermore, we clarify how to reduce the GAP modeling time and present experimental results comparing GAP with existing object detection methods, demonstrating that superior object detection with higher precision and recall rates is achieved by GAP.

Denighting: Enhancement of nighttime images for a surveillance camera

Nighttime images of a scene from a surveillance camera have lower contrast and higher noise than their corresponding daytime images of the same scene due to low illumination. Denighting is an image enhancement method for improving nighttime images, so that they are closer to those that would have been taken during daytime. The method exploits the fact that background images of the same scene have been captured all day long with a much higher quality. We present several results of the enhancement of low quality nighttime images using denighting.

Tracking method to random walk model based on orientation code matching

Image processing method that detects a particular moving object from an image by a fixed camera and tracking is noticed in various fields and it is a very important subject. In this paper, we propose a moving object tracking method that can cope with change of the area accompany the random walk movement of the moving object oneself and change of the brightness arise from change of the environmental such as a masking or change of the illumination. Proposal method can be robust processing for change of the illumination based on Orientation Code Matching that is demonstrated that is robust for the masking or change of the illumination. And, using Motion Vector derived from a continuity of the random walk model motion, under the condition that there are similar walk models, it can discriminate the walk model and individually tracking. Through the some experiment, this paper inspects the effectiveness of our proposed method.

A robust and real-time velocity sensor for agricultural vehicles

In this paper, we propose a velocity sensor for agricultural vehicles by sensing ground motion with robust image matching algorithm called Orientation Code Matching (OCM). The sensor performs velocity measurement with high accuracy and robustness without error by slipping in the fields. The algorithm of OCM is implemented on a Field Programmable Gate Array (FPGA) to perform real-time image matching and to reduce the size and power consumption. Because of low Power consumption, the sensor can be operate within the hermetically-sealed chassis so that it has high resistance to the environment. The effectiveness of the sensor has been verified by agricultural vehicles installed with the sensors in real agricultural fields.

Shape recognition of flexible cables by Outer Edge FCM clustering

A novel scheme for construction and representation of a single compound cable is presented. The complicated geometry of those objects put on natural posture is analysed and represented based on a modified clustering method: Outer Edge FCM. In the modification, the membership functions can be extended by introducing three evaluation functions for distance, angle, and reach, respectively. We introduce PCA to obtain rough change of shapes and to recognize thickness of cables in each segment. We propose Outer Edge FCM clustering to recognize complex shapes of outer parts of the objects. Then, we confirmed the availability of the proposed method by the experimental results of geometric representation of segment center vectors and vectors of outer edge.

3D measurement of flexible objects by robust motion stereo

We propose a novel three-dimensional measurement approach of flexible cables for factory automation applications, such as cable handling, connecter insertion without conflicts with cables by using robotic arms. The approach is based on motion stereo with a vision sensor. To solve stereo correspondence problem efficiently, feature point extraction from cables and a robust texture matching based feature tracking is applied. Additionally, by using stability analysis of the feature point tracking, defective feature points can be rejected and stable 3-D shape reconstruction is achieved. In our experiments, shapes of arch-like cables have been measured to an accuracy of 5 mm. It is enough to find connecters without conflicts with the cables.

A methods of separating weeds and trunk in different motions by blowing wind and a method of presuming root position

Due to the area of the vineyards in Hokkaido is extremely large, it is very difficult and hard to eradicate weeds by human being. In order to solve this problem, we developed a new dynamic image measure technique, which can be applied to the weeding robots in vineyards. The outstanding of this technique is that it can discriminate the weed and the trunk correctly and efficiently. Meanwhile, we also attempt to measure the root of trunk accurately. Due to techniques so far cannot suffice todays applications; a new method to measure the blocked trunk of grape in vineyards has also been developed in this paper.

Robust focusing by orientation code matching and its application to depth reconstruction

This paper has mainly discussed about two problems, object focusing and depth measurement. First, we propose a novel and robust scheme of image focusing by introducing a new measure of focusing based on Orientation code matching. A new evaluation function, named Complemental pencil volume, CPV, is defined and calculated to represent local sharpness of images, either in or out of focus, by comparing the similarity between any patterns extracted at the same position within their own scenes. An identified and unique maximum or peek, which of ill-condition scenes with low contrast observations. Experiments show that the OCM-based focusing is very robust to change in brightness, and to even more irregularities in the real imaging system, like dark condition. Second, based on this robust focusing technique, we applied it to an image sequence of an object surface to measure the depth of profile. A simple plane object surface has been implemented to demonstrate the basic approach. The results showed the successful and precision depth measurement of this object.

A fast tag searching method based on orientation code entropy and density

This paper aims to propose a fast image searching method from environmental observation images even in the presence of scale changes. A new scheme has been proposed for extracting feature areas as tags based on a robust image registration algorithm called Orientation code matching. Extracted tags are stored as template images and utilized in tag searching. As the number of tags grows, the searching cost becomes a serious problem. Additionally, change in viewing positions cause scale change of an image and matching failure. In our scheme, richness in features is important for tag generation and the entropy is used to evaluate the diversity of edge directions which are stable to scale change of the image. This characteristic contributes to limitation of searching area and reduction in calculation costs. Scaling factors are estimated by orientation code density which means the percentage of effective codes in fixed size tag areas. An estimated scaling factor is applied to matching a scale of template images to one of observation images. Some experiments are performed in order to compare computation time and verify effectiveness of estimated scaling factor using real scenes.

Using Extended Three-valued Increment Sign for a denoising model of high-frequency artifacts in JPEG images by estimation of specific frequency

This paper presents a robust denoising model for high-frequency artifacts resulted by compressing images into JPEG. In this model, the authors used only simple evaluation value named Extended Three-valued Increment Sign (ETIS). ETIS represents the relationship of adjacent pixels, which one is brighter or almost the same. The authors expected that ETIS difference between Compressed Image and Noise Image would be small except edge region. Then they figured out the sum of the squares of those differences and utilized it in noise estimation. Only quantization process cause the artifacts, then they optimized DCT coefficient matrix in non-linearly based on ETIS, and estimated high-frequency artifacts as an independent approach without smoothing process. In the result, the model succeeded to reject noise with preservation of edge information. In addition, they compared the results with others those applied the traditional method called ε-filter and made sure that their method had similar or better improvement.