An image recognition algorithm has been developed as part of a vision-based guidance system for row crops. Each combination of the vehicle guidance parameters, offset and heading angle, was treated as a 'pose'...
详细信息
An image recognition algorithm has been developed as part of a vision-based guidance system for row crops. Each combination of the vehicle guidance parameters, offset and heading angle, was treated as a 'pose' of the interested object, the crop rows. Whilst several pose recognitionalgorithms have previously been developed, the proposed algorithm is capable of determining the heading angle and the offset of a vehicle relative to the crop rows. A set of poses was collected and used as a training set. The training stage of the algorithm used the principal component analysis (Hotelling transform) to produce a low-dimensional eigenspace on which each pose was represented by its projections. Given a new image, the pose (heading angle and offset) recognition was done by projecting the image onto the eigenspace and determining the closest training image projection. Another set of poses was used to test the performance of the algorithm. Using different region of interest to train and test the algorithm, it presented the least average absolute error of 4.47 cm and 1.26 degrees for offset and heading angle, respectively, when using the central part of images for pose determination. (C) 2000 Silsoe Research Institute
The image feature extract method of image pattern recognitionalgorithm is studied in the paper. A high speed and real-time method of image locating and feature extract is presented. And the method mainly consists of ...
详细信息
ISBN:
(纸本)9780819470126
The image feature extract method of image pattern recognitionalgorithm is studied in the paper. A high speed and real-time method of image locating and feature extract is presented. And the method mainly consists of two key technologies, one is to locate the target area of measured object using mask matrix method, the other is to extract the edge feature based on the template matching method. The experiment results show that the method of image feature extracting is a high speed and high precision image recognition algorithm, and it can be satisfied the high-speed and real-time requests of on-line detection.
One of the trends of action recognition consists in extracting and comparing mid-level features which encode visual and motion aspects of objects into scenes. However, when scenes contain high-level semantic actions w...
详细信息
ISBN:
(纸本)9781479928392
One of the trends of action recognition consists in extracting and comparing mid-level features which encode visual and motion aspects of objects into scenes. However, when scenes contain high-level semantic actions with many interacting parts, these mid-level features are not sufficient to capture high level structures as well as high order causal relationships between moving objects resulting into a clear drop in performances. In this paper, we address this issue and we propose an alternative action recognition method based on a novel graph kernel. In the main contributions of this work, we first describe actions in videos using directed acyclic graphs (DAGs), that naturally encode pairwise interactions between moving object parts, and then we compare these DAGs by analyzing the spectrum of their sub-patterns that capture complex higher order interactions. This extraction and comparison process is computationally tractable, resulting from the acyclic property of DAGs, and it also defines a positive semi-definite kernel. When plugging the latter into support vector machines, we obtain an action recognitionalgorithm that overtakes related work, including graph-based methods, on a standard evaluation dataset.
In this paper we propose a low complexity method for Rotation, Scale and Translation (RST) invariant content-based image retrieval, suitable for a handheld imagerecognition device. The RST compensation method is base...
详细信息
In this paper we propose a low complexity method for Rotation, Scale and Translation (RST) invariant content-based image retrieval, suitable for a handheld imagerecognition device. The RST compensation method is based on Fourier-Mellin Transform (FMT) which we implement efficiently using log-polar grid interpolation. This RST compensation method is used in conjunction with an image recognition algorithm based on Discrete Cosine Transform (DCT) phase matching. A pre-selection algorithm is also added for decreasing the complexity. This algorithm is based on color proportions within concentric circular zones encompassing the edge pixels. The resulting RST invariant imagerecognition system was tested on 1500 pictograms and 1000 pictures with different RST conditions, showing an average recognition accuracy of 95.2% for pictograms and 96.9% for pictures.
An optical time-stretch flow imaging system enables high-throughput examination of cells/particles with unprecedented high speed and resolution. A significant amount of raw image data is produced. A highspeed cell rec...
详细信息
An optical time-stretch flow imaging system enables high-throughput examination of cells/particles with unprecedented high speed and resolution. A significant amount of raw image data is produced. A highspeed cell recognitionalgorithm is, therefore, highly demanded to analyze large amounts of data efficiently. A high-speed cell recognitionalgorithm consisting of two-stage cascaded detection and Gaussian mixture model (GMM) classification is proposed. The first stage of detection extracts cell regions. The second stage integrates distance transform and the watershed algorithm to separate clustered cells. Finally, the cells detected are classified by GMM. We compared the performance of our algorithm with support vector machine. Results show that our algorithm increases the running speed by over 150% without sacrificing the recognition accuracy. This algorithm provides a promising solution for high-throughput and automated cell imaging and classification in the ultrafast flow cytometer imaging platform. (C) 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)
Multi-level anticounterfeiting tags have been developed using a combination of different materials. Polyvinyl alcohol (PVA) mixed with titanium dioxide (TiO2) is used to produce flexible substrates. Fluorescent Opunti...
详细信息
Multi-level anticounterfeiting tags have been developed using a combination of different materials. Polyvinyl alcohol (PVA) mixed with titanium dioxide (TiO2) is used to produce flexible substrates. Fluorescent Opuntia Ficus-indica (OFI) extract dissolved with polymethyl methacrylate (PMMA) is then sprayed over the substrate to create a random, yet unique deposition of droplets. Photographs of the tags are taken under UV illumination at different angles and analyzed through the scale-invariant feature transform (SIFT) algorithm to extract their unique features. The SIFT analysis reveals hundreds to thousands of matched features when a given tag is compared with itself, whereas this number drops to tens for different tags. To enhance the security of the tags, ITO is sputtered onto one of them in the form of a pattern formed by a patch array exhibiting a specific fingerprint at terahertz (THz) frequencies. The evaluation of ITO reflectance shows that each patch array has a unique and unpredictable response stemming from its distinct electro-optical characteristics. The non-deterministic response of sprayed dye droplets and ITO patches enables the realization of two-level authentication, which is difficult to replicate at a reasonable cost. The simple manufacturing process and inexpensive materials involved make the proposed tags easily integrable into packaging.
The fire detection plays a critical role in the maintenance of public security. Previous approaches of early fire warning, based on smoke or temperature response must be set in the proximity of a fire. They cannot pro...
详细信息
The fire detection plays a critical role in the maintenance of public security. Previous approaches of early fire warning, based on smoke or temperature response must be set in the proximity of a fire. They cannot provide the additional information of fire location or size and are susceptible to complicated situations. It is still a big challenge to make rapid and accurate early fire warning in precombustion because of the lack of reliable alarm signals. Herein, a precursor molecular sensor (PMS) is designed and synthesized that can present the chemical structure transformation to form phthalocyanines (Pcs) and release a color change signal at about 180 degrees C, learning from the plant chlorophyll metabolism. Further, the PMS is assembled to an early fire warning component (EWC) and an intelligent image recognition algorithm is introduced for unburned fire detection. The EWC generates a colorful alarm within 20 s at 275 degrees C. Therefore, the facile PMS provides a reliable real-time monitoring strategy to the early fire warning detection in precombustion.
With increased range, the accuracy of longer-range linear displacement measurement is difficult to guarantee. According to the analysis, it is inevitable that there will be a certain margin between the direction of th...
详细信息
With increased range, the accuracy of longer-range linear displacement measurement is difficult to guarantee. According to the analysis, it is inevitable that there will be a certain margin between the direction of the calibration grating and the direction of the reading head, which will impact the longer-range linear displacement measurement. In order to eliminate this measurement error, a self-correction method based on 2-D synthesis is herein proposed. First, we describe the principle of absolute linear displacement measurement based on imagerecognition. Then, the error model is established, which caused by the included angle between the calibration grating and the reading head. Third, a method is proposed for obtaining the vertical offset of the calibration grating by using the vertical image sensor. Finally, we reach an error self-correction method based on 2-D synthesis. In order to test the feasibility of the proposed method, a linear displacement measuring device with a range of 200 mm was developed. After experiment, the maximum absolute error was reduced from 4.34 to 2.03 mu m with the proposed error correction in the long range of 200 mm. The proposed algorithm does not depend on the assembly and installation position, and can realize self-correction of errors. So the method could lay the groundwork for improving larger range linear displacement measurement technology.
In the application of vision measurement, the black light-absorbing object is difficult to reflect the structured light from infrared emitter of the RGB-D camera. Therefore, an image recognition algorithm based on ref...
详细信息
In the application of vision measurement, the black light-absorbing object is difficult to reflect the structured light from infrared emitter of the RGB-D camera. Therefore, an image recognition algorithm based on reference environment information is proposed to acquire the spatial positioning information of black volutes in the depalletizing system. The hardware system of the depalletizing system is mainly constructed of an upper computer, a six-axis industrial robot, an RGB-D camera and an end adsorption device. Firstly, the horizontal position information of each volute placed on the cardboard is obtained by the depth differences between the cardboard and the volute. Then, the depth information of the volute is obtained by the upper cardboard depth through collecting the position of the end vacuum suction cup triggered by feedback signal from vacuum generator. Secondly, a regional planar hand-eye calibration method is developed to improve the calibration accuracy in two-dimensional coordinates. The regional calibration method divides the robot working area into four regions: upper left, lower left, upper right, and lower right. The transformation matrix of each region is calculated separately. Finally, the depalletizing experiment is conducted on the three types of volutes. It is concluded that the average positioning error of the grasping center point of each volute obtained by our method is 3.795 mm, and its standard deviation is 1.769 mm. The average value of regional planar hand-eye calibration error is 4.044 mm, and its standard deviation is 1.501 mm. Under a stack of materials with dimensions of 1350 mm x 1350 mm x 1500 mm, the maximum error is controlled within 15 mm. Additionally, when combined with the end feedback compensation mechanism, the success rate for grasping all three volutes reaches 100%.
Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled-data and the rapid expansion of image categories raise the significant challenge of zero-shot learnin...
详细信息
ISBN:
(纸本)9781728132945
Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled-data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning (ZSL) aims to transfer knowledge from labeled classes into unlabeled classes to reduce human labeling effort. In this paper, we propose a novel progressive ensemble network model with multiple projected label embeddings to address zero-shot imagerecognition. The ensemble network is built by learning multiple image classification functions with a shared feature extraction network but different label embedding representations, which enhance the diversity of the classifiers and facilitate information transfer to unlabeled classes. A progressive training framework is then deployed to gradually label the most confident images in each unlabeled class with predicted pseudo-labels and update the ensemble network with the training data augmented by the pseudo-labels. The proposed model performs training on both labeled and unlabeled data. It can naturally bridge the domain shift problem in visual appearances and be extended to the generalized zero-shot learning scenario. We conduct experiments on multiple ZSL datasets and the empirical results demonstrate the efficacy of the proposed model.
暂无评论