Machine Vision and Applications
Công bố khoa học tiêu biểu
* Dữ liệu chỉ mang tính chất tham khảo
Sắp xếp:
How close are we to solving the problem of automated visual surveillance?
Machine Vision and Applications - Tập 19 - Trang 329-343 - 2007
The problem of automated visual surveillance has spawned a lively research area, with 2005 seeing three conferences or workshops and special issues of two major journals devoted to the topic. These alone are responsible for somewhere in the region of 240 papers and posters on automated visual surveillance before we begin to count those presented in more general fora. Many of these systems and algorithms perform one small sub-part of the surveillance task, such as motion detection. But even with low level image processing tasks it is often difficult to compare systems on the basis of published results alone. This review paper aims to answer the difficult question “How close are we to developing surveillance related systems which are really useful?” The first section of this paper considers the question of surveillance in the real world: installations, systems and practises. The main body of the paper then considers existing computer vision techniques with an emphasis on higher level processes such as behaviour modelling and event detection. We conclude with a review of the evaluative mechanisms that have grown from within the computer vision community in an attempt to provide some form of robust evaluation and cross-system comparability.
Hierarchical Gaussian descriptor based on local pooling for action recognition
Machine Vision and Applications - Tập 30 Số 2 - Trang 321-343 - 2019
Measurement of mirror surfaces using specular reflection and analytical computation
Machine Vision and Applications - Tập 24 - Trang 289-304 - 2012
In many applications, it is desirable to know three-dimensional information of mirror surfaces. However, the reflective characteristic of mirror surfaces makes many traditional three-dimensional reconstruction methods, such as stereovision or structured light scanning, fail. In this paper, a novel method is proposed to measure mirror surfaces. It is implemented with practical hardware and software that directly obtain analytic solutions for three-dimensional points on a mirror surface. Experimental results verified the effectiveness of the proposed method. In particular, this proposed method aims at providing an effective method to reconstruct specular weld pool surfaces which typically are highly dynamic and irregular. The capability to directly obtain analytic solutions for a set of points from a mirror surface as proposed and developed in this paper is a key to effectively measuring such highly dynamic and irregular mirror surfaces.
On the Use of Hash Functions as Preprocessing Algorithms to Detect Defects on Repeating Definite Textures
Machine Vision and Applications - Tập 17 - Trang 185-195 - 2006
Hash functions are one way functions and often used in cryptography to ensure the integrity of files by creating a binary signature specific to that file. In a similar way, a family of special hash functions can be developed and used to generate one dimensional signatures of an image. The resultant signatures can then be used to compare the image either to a golden template or, if the image consists of repeating definite patterns, then to the texture itself. While such hash functions are sensitive enough to detect small changes and defects in repeating texture, they are immune to changes in illumination and contrast. In this paper we discuss the generation of suitable hash functions for textured images, which are simple enough to fit into a very small FPGA, and provide several examples of their use.
Multi-cue hand detection and tracking for a head-mounted augmented reality system
Machine Vision and Applications - Tập 24 - Trang 931-946 - 2013
With the recent developments in wearable augmented reality (AR), the role of natural human–computer interaction is becoming more important. Utilization of auxiliary hardware for interaction introduces extra complexity, weight and cost to wearable AR systems and natural means of interaction such as gestures are therefore more desirable. In this paper, we present a novel multi-cue hand detection and tracking method for head-mounted AR systems which combines depth, color, intensity and curvilinearity. The combination of different cues increases the detection rate, eliminates the background regions and therefore increases the tracking performance under challenging conditions. Detected hand positions and the trajectories are used to perform actions such as click, select, etc. Moreover, the 6 DOF poses of the hands are calculated by approximating the segmented regions with planes in order to render a planar menu (interface) around the hand and use the hand as a planar selection tool. The proposed system is tested on different scenarios (including markers for reference) and the results show that our system can detect and track the hands successfully in challenging conditions such as cluttered and dynamic environments and illumination variance. The proposed hand tracker outperforms other well-known hand trackers under these conditions.
Hệ thống chấm điểm và học tập tương tác cho thư pháp Trung Quốc Dịch bởi AI
Machine Vision and Applications - Tập 19 - Trang 43-55 - 2007
Thư pháp Trung Quốc là một nghệ thuật phương Đông. Trong bài báo này, một hệ thống hướng dẫn thư pháp tương tác được đề xuất lần đầu tiên để đánh giá điểm số của chữ viết bằng cách sử dụng kỹ thuật xử lý ảnh và suy diễn mờ. Các tài liệu viết được phân đoạn tự động. Ba đặc trưng được định lượng, bao gồm tâm, kích thước và các proejction của từng ký tự viết, được trích xuất để đo điểm số thư pháp. Hệ thống cũng cung cấp một số hướng dẫn cải thiện cho người dùng. Một số kết quả thí nghiệm được đưa ra để chứng minh tính hợp lệ và hiệu quả của hệ thống được đề xuất. Thông qua hệ thống hữu ích này, người dùng có thể học và thực hành thư pháp Trung Quốc tại nhà.
#thư pháp Trung Quốc #hệ thống tương tác #xử lý ảnh #suy diễn mờ #học tập #đánh giá điểm số
Cross-validation of a semantic segmentation network for natural history collection specimensAbstract
Machine Vision and Applications - Tập 33 Số 3 - 2022
Semantic segmentation has been proposed as a tool to accelerate the processing of natural history collection images. However, developing a flexible and resilient segmentation network requires an approach for adaptation which allows processing different datasets with minimal training and validation. This paper presents a cross-validation approach designed to determine whether a semantic segmentation network possesses the flexibility required for application across different collections and institutions. Consequently, the specific objectives of cross-validating the semantic segmentation network are to (a) evaluate the effectiveness of the network for segmenting image sets derived from collections different from the one in which the network was initially trained on; and (b) test the adaptability of the segmentation network for use in other types of collections. The resilience to data variations from different institutions and the portability of the network across different types of collections are required to confirm its general applicability. The proposed validation method is tested on the Natural History Museum semantic segmentation network, designed to process entomological microscope slides. The proposed semantic segmentation network is evaluated through a series of cross-validation experiments designed to test using data from two types of collections: microscope slides (from three institutions) and herbarium sheets (from seven institutions). The main contribution of this work is the method, software and ground truth sets created for this cross-validation as they can be reused in testing similar segmentation proposals in the context of digitization of natural history collections. The cross-validation of segmentation methods should be a required step in the integration of such methods into image processing workflows for natural history collections.
Convolutional neural networks based on multi-scale additive merging layers for visual smoke recognition
Machine Vision and Applications - Tập 30 - Trang 345-358 - 2018
Traditional smoke recognition methods are mainly based on handcrafted features. However, it is difficult to design handcrafted features that are robust and discriminative for smoke recognition because of large variations in smoke color, shapes and textures. To solve this problem, we specifically design a basic block of convolutional neural networks (CNNs) and stack basic blocks to propose a novel deep multi-scale CNN (DMCNN) for smoke recognition. The basic block consists of several parallel convolutional layers with the same number of filters but different kernel sizes for scale invariance. Each convolutional layer is followed by a batch normalization to normalize the output of the convolutional layer. Then the basic block sums up all normalized outputs from multi-scale parallel layers and activates the sum as the final output of the block. To fully extract scale invariant features, we cascade eleven basic blocks, which is followed by a global average pooling and a 2D fully connected layer, to construct DMCNN. Experimental results show that our method achieves higher detection rates, higher accuracy rates and lower false alarm rates than existing methods. To further verify the efficiency of DMCNN, we also conducted face gender recognition experiments on the LFW database and our model also achieves obviously higher accuracy rates than other methods. Furthermore, our method is an efficient, lightweight CNN model with about 1 M parameters that are far less than other CNN methods.
Unsupervised learning of probabilistic subspaces for multi-spectral and multi-temporal image-based disaster mapping
Machine Vision and Applications - Tập 34 - Trang 1-16 - 2023
Accurate and timely identification of regions damaged by a natural disaster is critical for assessing the damages and reducing the human life cost. The increasing availability of satellite imagery and other remote sensing data has triggered research activities on development of algorithms for detection and monitoring of natural events. Here, we introduce an unsupervised subspace learning-based methodology that uses multi-temporal and multi-spectral satellite images to identify regions damaged by natural disasters. It first performs region delineation, matching, and fusion. Next, it applies subspace learning in the joint regional space to produce a change map. It identifies the damaged regions by estimating probabilistic subspace distances and rejecting the non-disaster changes. We evaluated the performance of our method on seven disaster datasets including four wildfire events, two flooding events, and a earthquake/tsunami event. We validated our results by calculating the dice similarity coefficient (DSC), and accuracy of classification between our disaster maps and ground-truth data. Our method produced average DSC values of 0.833 and 0.736, for wildfires and floods, respectively, and overall DSC of 0.855 for the tsunami event. The evaluation results support the applicability of our method to multiple types of natural disasters.
Tổng số: 1,334
- 1
- 2
- 3
- 4
- 5
- 6
- 10