Understanding crowd dynamics is an interesting problem in computervision owing to its various applications. We propose a dynamical system to model the dynamics of collective motion of the crowd. The model learns the ...
详细信息
ISBN:
(纸本)9781450347532
Understanding crowd dynamics is an interesting problem in computervision owing to its various applications. We propose a dynamical system to model the dynamics of collective motion of the crowd. The model learns the spatio-temporal interaction pattern of the crowd from the track data captured over a time period. The model is trained under a least square formulation with spatial and temporal constraints. The spatial constraint allows the model to consider only the neighbors of a particular agent and the temporal constraint enforces temporal smoothness in the model. We also propose an effective group detection algorithm that utilizes the eigenvectors of the interaction matrix of the model. The group detection is cast as a spectral clustering problem. Extensive experimentation demonstrates a superlative performance of our group detection algorithm over state-of-the-art methods.
Dictionary learning has been used to solve inverse problems in imaging and as an unsupervised feature extraction tool in vision. The main disadvantage of dictionary learning for applications in vision is the relativel...
详细信息
ISBN:
(纸本)9781450347532
Dictionary learning has been used to solve inverse problems in imaging and as an unsupervised feature extraction tool in vision. The main disadvantage of dictionary learning for applications in vision is the relatively long feature extraction time during testing;owing to the requirement of solving an iterative optimization problem (10-minimization). The newly developed analysis framework of transform learning does not suffer from this shortcoming;feature extraction only requires a matrix vector multiplication. This work proposes an alternate formulation for transform learning that improves the accuracy even further. Experiments on benchmark databases show that our proposed transform learning yields results better than dictionary learning, autoencoder (AE) and restricted Boltzmann machine (RBM). The feature extraction time is fast as AE and RBM.
Compressed sensing magnetic resonance imaging (CSMRI) have demonstrated that it is possible to accelerate MRI scan time by reducing the number of measurements in the k-space without significant loss of anatomical deta...
详细信息
ISBN:
(纸本)9781450347532
Compressed sensing magnetic resonance imaging (CSMRI) have demonstrated that it is possible to accelerate MRI scan time by reducing the number of measurements in the k-space without significant loss of anatomical details. The number of k-space measurements is roughly proportional to the sparsity of the MR signal under consideration. Recently, a few works on CSMRI have revealed that the sparsity of the MR signal can be enhanced by suitable weighting of different regularization priors. In this paper, we have proposed an efficient adaptive weighted reconstruction algorithm for the enhancement of sparsity of the MR image. Experimental results show that the proposed algorithm gives better reconstructions with less number of measurements without significant increase of the computational time compared to existing algorithms in this line.
We propose a novel deep framework, TraCount, for highly overlapping vehicle counting in congested traffic scenes. TraCount uses multiple fully convolutional(FC) sub-networks to predict the density map for a given stat...
详细信息
ISBN:
(纸本)9781450347532
We propose a novel deep framework, TraCount, for highly overlapping vehicle counting in congested traffic scenes. TraCount uses multiple fully convolutional(FC) sub-networks to predict the density map for a given static image of a traffic scene. The different FC sub-networks provide a range in size of receptive fields that enable us to count vehicles whose perspective effect varies significantly in a scene due to the large visual field of surveillance cameras. The predictions of different FC sub-networks are fused by weighted averaging to obtain a final density map. We show that TraCount outperforms the state of the art methods on the challenging TRANCOS dataset that has a total of 46796 vehicles annotated across 1244 images.
One of the common image forgery techniques is the splicing, where parts from different images are copied and pasted onto a single image. This paper proposes a new forensics method for detecting splicing forgeries in i...
详细信息
ISBN:
(纸本)9781450347532
One of the common image forgery techniques is the splicing, where parts from different images are copied and pasted onto a single image. This paper proposes a new forensics method for detecting splicing forgeries in images containing human faces. Our approach is based on extracting an illumination-signature from the faces of people present in an image using the dichromatic reflection model (DRM). The dichromatic plane histogram (DPH), which is calculated by applying the 2D Hough Transform on the face images, is used as the illumination-signature. The correlation measure is employed to compute the similarity between the DPHs obtained from different faces present in an image. Finally, a simple threshold on this similarity measure exposes splicing forgeries in the image. Experimental results show the efficacy of the proposed method.
Object recognition is one of the challenging tasks in computervision and the problem becomes increasingly difficult when the image categories are visually correlated among themselves i.e. they are visually similar an...
详细信息
ISBN:
(纸本)9781450347532
Object recognition is one of the challenging tasks in computervision and the problem becomes increasingly difficult when the image categories are visually correlated among themselves i.e. they are visually similar and only fine differences exist among the categories. This paper has a two-fold objective which involves organization of the image categories in a hierarchical tree like structure using self tuning spectral clustering for exploiting the correlations among them. The organization phase is followed by a node specific large margin nearest neighbor classification scheme, where a Mahalnobis distance metric is learnt for each non-leaf node. Further a procedure for hyperparameters selection has been discussed w.r.t two strategies i.e. grid search and Bayesian optimization. The proposed algorithm's effectiveness is tested on selected classes of the popular imagenet dataset.
Virtual garments like shirts and trousers are created from 2D patterns stitched over 3D models. However, indian garments, like dhotis and saris, pose a unique draping challenge for physically-simulated garment systems...
详细信息
ISBN:
(纸本)9781450347532
Virtual garments like shirts and trousers are created from 2D patterns stitched over 3D models. However, indian garments, like dhotis and saris, pose a unique draping challenge for physically-simulated garment systems, as they are not stitched garments. We present a method to intuitively specify the parameters governing the drape of an indian garment using a sketch-based interface. We then interpret the sketch strokes to procedural, physically-simulated draping routines to wrap, pin and tuck the garments around the body mesh as needed. After draping, the garments are ready to be simulated and used during animation as required. We present several examples of our draping technique.
Facial expressions convey rich information about emotions, intentions and other internal states of a person. Automatic facial expression and cartoonification systems are aiming towards the application of computer visi...
详细信息
ISBN:
(纸本)9781450347532
Facial expressions convey rich information about emotions, intentions and other internal states of a person. Automatic facial expression and cartoonification systems are aiming towards the application of computervision systems in human computer interaction, emotion analysis, medical care, virtual learning and even entertainment. In this paper, we propose an identity-independent robust system to detect human expression and generate their corresponding cartoonified images in real-time using smart-devices. Identity-independent expression recognition system enhances the facial features of query face image using its intra-class variation image and classifies using support vector machines. The method is robust to variation in identity and illumination of the query face image. Along with the basic expressions, like angry, happy and sad, we have also successfully detected the emotional states of sleepy and pain. The experimental results on JAFFE, CK+, PICS, Yalefaces, and Senthil databases show the effectiveness of the system.
Given a set of sequential exposures, High Dynamic Range imaging is a popular method for obtaining high-quality images for fairly static scenes. However, this typically suffers from ghosting artifacts for scenes with s...
详细信息
ISBN:
(纸本)9781450347532
Given a set of sequential exposures, High Dynamic Range imaging is a popular method for obtaining high-quality images for fairly static scenes. However, this typically suffers from ghosting artifacts for scenes with significant motion. Also, existing techniques cannot handle heavily saturated regions in the sequence. In this paper, we propose an approach that handles both the issues mentioned above. We achieve robustness to motion (both object and camera) and saturation via an energy minimization formulation with spatio-temporal constraints. The proposed approach leverages information from the neighborhood of heavily saturated regions to correct such regions. The experimental results demonstrate the superiority of our method over state-of-the-art techniques for a variety of challenging dynamic scenes.
The problem of tracking ball in a soccer video is challenging because of sudden change in speed and orientation of the soccer ball. Successful tracking in such a scenario depends on the ability of the algorithm to bal...
详细信息
ISBN:
(纸本)9781450347532
The problem of tracking ball in a soccer video is challenging because of sudden change in speed and orientation of the soccer ball. Successful tracking in such a scenario depends on the ability of the algorithm to balance prior constraints continuously against the evidence garnered from the sequences of images. This paper proposes a particle filter based algorithm that tracks the ball when it changes its direction suddenly or takes high speed. Exact, deterministic tracking algorithms based on discretized functional, suffer from severe limitations in the form of prior constraints. Our tracking algorithm has shown excellent result even for partial occlusion which is a major concern in soccer video. We have shown that the proposed tracking algorithm is at least 7.2% better compared to competing approaches for soccer ball tracking.
暂无评论