In this paper, we propose a novel method of reconstructing 3D shapes from single-view images based on an adversarial refiner. Generative Adversarial mechanism is adopted between the coarse-volumes generation stage and...
详细信息
Moving objects classification in traffic scene videos is a hot topic in recent years. It has significant meaning to intelligent traffic system by classifying moving traffic objects into pedestrians, motor vehicles, no...
详细信息
ISBN:
(纸本)9781457701221
Moving objects classification in traffic scene videos is a hot topic in recent years. It has significant meaning to intelligent traffic system by classifying moving traffic objects into pedestrians, motor vehicles, non-motor vehicles etc.. Traditional machine learning approaches make the assumption that source scene objects and target scene objects share same distributions, which does not hold for most occasions. Under this circumstance, large amount of manual labeling for target scene data is needed, which is time and labor consuming. In this paper, we introduce TrAdaBoost, a transfer learning algorithm, to bridge the gap between source and target scene. During training procedure, TrAdaBoost makes full use of the source scene data that is most similar to the target scene data so that only small number of labeled target scene data could help improve the performance significantly. The features used for classification are Histogram of Oriented Gradient features of the appearance based instances. The experiment results show the outstanding performance of the transfer learning method comparing with traditional machine learning algorithm.
This paper proposes a new image denoising method based on the NonsubSampled Contourlet Transform (NSCT) and the bivariate model under the framework of Bayesian MAP estimation theory. The proposed algorithm uses the NS...
详细信息
This paper proposes a new image denoising method based on the NonsubSampled Contourlet Transform (NSCT) and the bivariate model under the framework of Bayesian MAP estimation theory. The proposed algorithm uses the NSCT's advantages of translation-invariant and multidirection-selectivity, exploits the intra-scale and inter-scale correlations of NSCT coefficients, and elaborates the method of noise estimation. Compared with some current outstanding denoising methods, the simulation results and analysis show that the proposed algorithm obviously outperforms in both Peak Signal-to-Noise Ratio (PSNR) and visual quality, and effectively preserves detail and texture information of original images.
A key problem of image Based Visual Servo (IBVS) System is to track objects in image sequences. Thus, the tracking algorithm plays an important role in improving the efficiency of IBVS systems. In this paper, a novel ...
详细信息
ISBN:
(纸本)9781457701221
A key problem of image Based Visual Servo (IBVS) System is to track objects in image sequences. Thus, the tracking algorithm plays an important role in improving the efficiency of IBVS systems. In this paper, a novel tracking algorithm called Modified CamShift Guided Particle Filter (MCAMSGPF) is proposed, which interpolated Speeded-Up Robust Features (SURF) into the framework of conventional CamShift Guided Particle Filter (CAMSGPF) tracking method. This new algorithm outperforms conventional CAMSGPF and other baseline trackers with respect to tracking robustness in the clutter background of similar colors and occlusions. We also proposed a new system model to implement and test the new algorithm in a real time moving IBVS system, which is applied in a mobile robot with an on-board camera.
Recently, human action recognition has been a popular and important topic in computer vision. However, except some conventional problems such as noise, low resolution etc., viewinvariant recognition is one of the most...
详细信息
ISBN:
(纸本)9781457701221
Recently, human action recognition has been a popular and important topic in computer vision. However, except some conventional problems such as noise, low resolution etc., viewinvariant recognition is one of the most challenging problems. In this paper, we focus on solve multi-view action recognition from surveillance video. To detect moving objects from complicated backgrounds, this paper employs improved Gaussian mixed model, which uses K-means clustering to initialize the model and it gets better motion detection results for surveillance videos. We demonstrate the silhouette representation ”Envelope Shape” can solve the viewpoint problem in surveillance videos. The experiment results demonstrate that our human action recognition system is fast and efficient on CASIA activity analysis database.
Fuzzy enhancement is applied in computer aided diagnosis of liver cancer from B mode ultrasound images as a pre-processing procedure in this paper. It was evaluated with three classifiers including K means, back propa...
详细信息
Electroencephalography (EEG) is widely used in the field of neural engineering. EEG signals can describe the brain activities while the subjects with para/tetraplegia perform movement with their limbs. This paper revi...
详细信息
Traditional recurrent neural networks are composed of capacitors, inductors, resistors, and operational *** neural networks are constructed by replacing resistors with memristors. This paper focuses on the memory anal...
详细信息
Traditional recurrent neural networks are composed of capacitors, inductors, resistors, and operational *** neural networks are constructed by replacing resistors with memristors. This paper focuses on the memory analysis,i.e. the initial value computation, of memristors. Firstly, we present the memory analysis for a single memristor based on memristors’ mathematical models with linear and nonlinear ***, we present the memory analysis for two memristors in series and parallel. Thirdly, we point out the difference between traditional neural networks and those that are memristive. Based on the current and voltage relationship of memristors, we use mathematical analysis and SPICE simulations to demonstrate the validity of our methods.
An improved Zernike moment using a region-based shape descriptor is presented. The improved Zernike moment not only has rotation invariance, but also has scale invariance that the unimproved Zernike moment does not ha...
详细信息
Semisupervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previ...
详细信息
暂无评论