Various human detection algorithms are limited in capability due to the lack of using other supplemental algorithms for enhancing detection. We propose using two different algorithms to extract vital information to augment human detection algorithms for increased accuracy. The first algorithm is the computation of depth information. Information needed to obtain depth is based on the specific location of the camera based from frame to frame. Most calibrated stereo cameras can develop accurate depth information, but the motion that takes place from frame to frame can be utilized for developing rough depth perception of the objects in the scene. Block-matching and optical flow algorithms can be used to provide these disparities that happen in the image, which will provide depth information for the human detection algorithm. The second algorithm is superpixel segmentation. This algorithm determines a rough over-segmentation of the imagery, which well defines the boundaries as larger pixels that are within the imagery. This information can be used to distinguish background and foreground information to create a specific segmentation around the human detection, rather than a bounding box detection that may include various background information. The fusion of these algorithms with human detection has been shown to increase detection accuracy and providing better localization of the human in the imagery.
Today, it is increasingly frequent and easy to digitize the surface of real 3D objects. However, the obtained meshes are often inaccurate and noisy. In this paper, we present a method to segment a digitized 3D surface from a real object by analyzing its curvature. Experimental results – applied on real digitized 3D meshes – show the efficiency of our proposed analysis, particularly in a reverse engineering process.
The problem of identifying materials in dual-energy CT images arises in many applications in medicine and security. In this paper, we introduce a new algorithm for joint segmentation and classification of material regions. In our algorithm, we learn an appearance model for patches of pixels that captures the correlation in observed values among neighboring pixels/voxels. We pose the joint segmentation/classification problem as a discrete optimization problem using a Markov random field model for correlation of class labels among neighboring patches, and solve the problem using graph cut techniques. We evaluate the performance of the proposed method using both simulated phantoms and data collected from a medical scanner. We show that our algorithm outperforms the alternative approaches in which the appearance model is based on pixel values instead of patches.
This paper presents an accurate and robust surgical instrument recognition algorithm to be used as part of a Robotic Scrub Nurse (RSN). Surgical instruments are often cluttered, occluded and displaying specular light, which cause a challenge for conventional vision algorithms. A learning-through-interaction paradigm was proposed to tackle this challenge. The approach combines computer vision with robot manipulation to achieve active recognition. The unknown instrument is firstly segmented out as blobs and its poses estimated, then the RSN system picks it up and presents it to an optical sensor in an established pose. Lastly the unknown instrument is recognized with high confidence. Experiments were conducted to evaluate the performance of the proposed segmentation and recognition algorithms, respectively. It is found out that the proposed patch-based segmentation algorithm and the instrument recognition algorithm greatly outperform their benchmark comparisons. Such results indicate the applicability and effectiveness of our RSN system in performing accurate and robust surgical instrument recognition.