Search

A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video frames. With the video imprint representation, it is convenient to reverse map back to both temporal and spatial locations in video frames, allowing for both key frame identification and key areas localization within each frame. In the proposed framework, a dedicated feature alignment module is incorporated for redundancy removal across frames to produce the tensor representation, i.e., the video imprint. Subsequently, the video imprint is individually fed into both a reasoning network and a feature aggregation module, for event recognition/recounting and event retrieval tasks, respectively. Thanks to its attention mechanism inspired by the memory networks used in language modeling, the proposed reasoning network is capable of simultaneous event category recognition and localization of the key pieces of evidence for event recounting. In addition, the latent structure in our reasoning network highlights the areas of the video imprint, which can be directly used for event recounting. With the event retrieval task, the compact video representation aggregated from the video imprint contributes to better retrieval results than existing state-of-the-art methods.

Biodiversity conservation depends on accurate, up-to-date information about wildlife population distributions. Motion-activated cameras, also known as camera traps, are a critical tool for population surveys, as they are cheap and non-intrusive. However, extracting useful information from camera trap images is a cumbersome process: a typical camera trap survey may produce millions of images that require slow, expensive manual review. Consequently, critical information is often lost due to resource limitations, and critical conservation questions may be answered too slowly to support decision-making. Computer vision is poised to dramatically increase efficiency in image-based biodiversity surveys, and recent studies have harnessed deep learning techniques for automatic information extraction from camera trap images. However, the accuracy of results depends on the amount, quality, and diversity of the data available to train models, and the literature has focused on projects with millions of relevant, labeled training images. Many camera trap projects do not have a large set of labeled images and hence cannot benefit from existing machine learning techniques. Furthermore, even projects that do have labeled data from similar ecosystems have struggled to adopt deep learning methods because image classification models overfit to specific image backgrounds (i.e., camera locations). In this paper, we focus not on automating the labeling of camera trap images, but on accelerating this process. We combine the power of machine intelligence and human intelligence to build a scalable, fast, and accurate active learning system to minimize the manual work required to identify and count animals in camera trap images. Our proposed scheme can match the state of the art accuracy on a 3.2 million image dataset with as few as 14,100 manual labels, which means decreasing manual labeling effort by over 99.5%., 15 pages, 5 figures

In recent scene recognition research images or large image regions are often represented as disorganized "bags" of features which can then be analyzed using models originally developed to capture co-variation of word counts in text. However, image feature counts are likely to be constrained in different ways than word counts in text. For example, as a camera pans upwards from a building entrance over its first few floors and then further up into the sky Fig. 1, some feature counts in the image drop while others rise -- only to drop again giving way to features found more often at higher elevations. The space of all possible feature count combinations is constrained both by the properties of the larger scene and the size and the location of the window into it. To capture such variation, in this paper we propose the use of the counting grid model. This generative model is based on a grid of feature counts, considerably larger than any of the modeled images, and considerably smaller than the real estate needed to tile the images next to each other tightly. Each modeled image is assumed to have a representative window in the grid in which the feature counts mimic the feature distribution in the image. We provide a learning procedure that jointly maps all images in the training set to the counting grid and estimates the appropriate local counts in it. Experimentally, we demonstrate that the resulting representation captures the space of feature count combinations more accurately than the traditional models, not only when the input images come from a panning camera, but even when modeling images of different scenes from the same category., Comment: The counting grid code is available at www.alessandroperina.com

Models that captures the common structure of an object class have appeared few years ago in the literature (Jojic and Caspi in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 212---219, 2004; Winn and Jojic in Proceedings of International Conference on Computer Vision (ICCV), pp. 756---763, 2005); they are often referred as "stel models." Their main characteristic is to segment objects in clear, often semantic, parts as a consequence of the modeling constraint which forces the regions belonging to a single segment to have a tight distribution over local measurements, such as color or texture. This self-similarity within a region in a single image is typical of many meaningful image parts, even when across different images of similar objects, the corresponding parts may not have similar local measurements. Moreover, the segmentation itself is expected to be consistent within a class, although still flexible. These models have been applied mostly to segmentation scenarios. In this paper, we extent those ideas (1) proposing to capture correlations that exist in structural elements of an image class due to global effects, (2) exploiting the segmentations to capture feature co-occurrences and (3) allowing the use of multiple, eventually sparse, observation of different nature. In this way we obtain richer models more suitable to recognition tasks. We accomplish these requirements using a novel approach we dubbed stel component analysis. Experimental results show the flexibility of the model as it can deal successfully with image/video segmentation and object recognition where, in particular, it can be used as an alternative of, or in conjunction with, bag-of-features and related classifiers, where stel inference provides a meaningful spatial partition of features.

Dimensionality reduction techniques such as principal component analysis and factor analysis are used to discover a linear mapping between high-dimensional data samples and points in a lower-dimensional subspace. Previously, Frey and Jojic introduced transformation-invariant component analysis (TCA) to learn a linear mapping, invariant to a set of known form of global transformations. However, parameter estimation in that model using the previously-proposed expectation maximization (EM) algorithm required scalar operations in the order of N2 where N is the dimensionality of each training example. This is prohibitive for many applications of interest such as modeling mid-to large-size images, where, for instance, i>N may be as high as 786432 (512×512 RGB image). In this paper, we present an efficient algorithm that reduces the computational requirements to order of NlogN. With this speedup, we show the effectiveness of transformation-invariant component analysis in various applications including tracking, learning video textures, clustering, object recognition and object detection in images. Software for TCA can be downloaded from http://www.psi.toronto.edu/fastTCA.htm

Recently, "epitomes" were introduced as patch-based probability models that are learned by compiling together a large number of examples of patches from input images. In this paper, we describe how epitomes can be used to model video data and we describe significant computational speedups that can be incorporated into the epitome inference and learning algorithm. In the case of videos, epitomes are estimated so as to model most of the small space-time cubes from the input data. Then, the epitome can be used for various modeling and reconstruction tasks, of which we show results for video super-resolution, video interpolation, and object removal. Besides computational efficiency, an interesting advantage of the epitome as a representation is that it can be reliably estimated even from videos with large amounts of missing data. We illustrate this ability on the task of reconstructing the dropped frames in video broadcast using only the degraded video and also in denoising a severely corrupted video.

We derive a statistical graphical model of video scenes with multiple, possibly occluded objects that can be efficiently used for tasks related to video search, browsing and retrieval. The model is trained on query (target) clip selected by the user. Shot retrieval process is based on the likelihood of a video frame under generative model. Instead of using a combination of weighted Euclidean distances as a shot similarity measure, the likelihood model automatically separates and balances various causes of variability in video, including occlusion, appearance change and motion. Thus, we overcome tedious and complex user interventions required in previous studies. We use the model in the adaptive video forward application that adapts video playback speed to the likelihood of the data. The similarity measure of each candidate clip to the target clip defines the playback speed. Given a query, the video is played at a higher speed as long as video content has low likelihood, and when frames similar to the query clip start to come in, the video playback rate drops. Set of experiments o12n typical home videos demonstrate performance, easiness and utility of our application.

We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it by developing a new algorithm for tracking a moving object in a cluttered, noisy scene using two microphones and a camera. Our model uses unobserved variables to describe the data in terms of the process that generates them. It is therefore able to capture and exploit the statistical structure of the audio and video data separately, as well as their mutual dependencies. Model parameters are learned from data via an EM algorithm, and automatic calibration is performed as part of this procedure. Tracking is done by Bayesian inference of the object location from data. We demonstrate successful performance on multimedia clips captured in real world scenarios using off-the-shelf equipment.

Clustering is a simple, effective way to derive useful representations of data, such as images and videos. Clustering explains the input as one of several prototypes, plus noise. In situations where each input has been randomly transformed (e.g., by translation, rotation, and shearing in images and videos), clustering techniques tend to extract cluster centers that account for variations in the input due to transformations, instead of more interesting and potentially useful structure. For example, if images from a video sequence of a person walking across a cluttered background are clustered, it would be more useful for the different clusters to represent different poses and expressions, instead of different positions of the person and different configurations of the background clutter. We describe a way to add transformation invariance to mixture models, by approximating the nonlinear transformation manifold by a discrete set of points. We show how the expectation maximization algorithm can be used to jointly learn clusters, while at the same time inferring the transformation associated with each input. We compare this technique with other methods for filtering noisy images obtained from a scanning electron microscope, clustering images from videos of faces into different categories of identification and pose and removing foreground obstructions from video. We also demonstrate that the new technique is quite insensitive to initial conditions and works better than standard techniques, even when the standard techniques are provided with extra data.

We present computer vision techniques for building dressed human models using images. We develop an algorithm for three-dimensional body reconstruction and texture mapping using contour, stereo, and texture information from several images and deformable superquadrics as the model parts. We demonstrate a novel vision technique for analysis of cloth draping behavior. This technique allows for estimation of cloth model parameters, such as bending properties, but can also be used to estimate the contact points between the body and clothing in the range data of dressed humans. Combined with our body reconstruction algorithm and additional constraints on the articulation model, the detection of the garment-body contact points allows construction of a dressed human model in which even the geometry that was covered by clothing in the available data is reasonably well estimated.

Recently, the Counting Grid (CG) model was developed to represent each input image as a point in a large grid of feature counts. This latent point is a corner of a window of grid points which are all uniformly combined to match the (normalized) feature counts in the image. Being a bag of word model with spatial layout in the latent space, the CG model has superior handling of field of view changes in comparison to other bag of word models, but with the price of being essentially a mixture, mapping each scene to a single window in the grid. In this paper we introduce a family of componential models, dubbed the Componential Counting Grid, whose members represent each input image by multiple latent locations, rather than just one. In this way, we make a substantially more flexible admixture model which captures layers or parts of images and maps them to separate windows in a Counting Grid. We tested the models on scene and place classification where their componential nature helped to extract objects, to capture parallax effects, thus better fitting the data and outperforming Counting Grids and Latent Dirichlet Allocation, especially on sequences taken with wearable cameras.

Adopting the Counting Grid (CG) representation [1], the Spring Lattice Counting Grid (SLCG) model uses a grid of feature counts to capture the spatial layout that a variety of images tend to follow. The images are mapped to the counting grid with their features rearranged so as to strike a balance between the mapping quality and the extent of the necessary rearrangement. In particular, the feature sets originating from different image sectors are mapped to different sub-windows in the counting grid in a configuration that is close, but not exactly the same as the configuration of the source sectors. The distribution over deformations of the sector configuration is learnable using a new spring lattice model, while the rearrangement of features within a sector is unconstrained. As a result, the CG model gains a more appropriate level of invariance to realistic image transformations like view point changes, rotations or scales. We tested SLCG on standard scene recognition datasets and on a dataset collected with a wearable camera which recorded the wearer's visual input over three weeks. Our algorithm is capable of correctly classifying the visited locations more than 80% of the time, outperforming previous approaches to visual location recognition. At this level of performance, a variety of real-world applications of wearable cameras become feasible.

In recent object/scene recognition research images or large image regions are often represented as disorganized ”bags” of image features. This representation allows direct application of models of word counts in text. However, the image feature counts are likely to be constrained in different ways than word counts in text. As a camera pans upwards from a building entrance over its first few floors and then above the penthouse to the backdrop formed by the mountains, and then further up into the sky, some feature counts in the image drop while others rise–only to drop again giving way to features found more often at higher elevations (Fig. 1). The space of all possible feature count combinations is constrained by the properties of the larger scene as well as the size and the location of the window into it. Accordingly, our model is based on a grid of feature counts, considerably larger than any of the modeled images, and considerably smaller than the real estate needed to tile the images next to each other tightly. Each modeled image is assumed to have a representative window in the grid in which the sum of feature counts mimics the distribution in the image. We provide learning procedures that jointly map all images in the training set to the counting grid and estimate the appropriate local counts in it. Experimentally, we demonstrate that the resulting representation captures the space of feature count combinations more accurately than the traditional models, such as latent Dirichlet allocation, even when modeling images of different scenes from the same category.

We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment multiple images into a consistent set of image regions. The segmentations are provided at several levels of granularity and links among them are automatically provided. Model training and inference in it is faster than most local feature extraction algorithms, and yet the provided image segmentation, and the segment matching among images provide a rich backdrop for image recognition, segmentation and registration tasks.

As a useful concept in the study of the low level image class structure, we introduce the notion of a structure element - `stel.' The notion is related to the notions of a pixel, superpixel, segment or a part, but instead of referring to an element or a region of a single image, stel is a probabilistic element of an entire image class. Stels often define clear object or scene parts as a consequence of the modeling constraint which forces the regions belonging to a single stel to have a tight distribution over local measurements, such as color or texture. This self-similarity within a region in a single image is typical of most meaningful image parts, even when in different images of similar objects the corresponding parts may not have similar local measurements. The stel itself is expected to be consistent within a class, yet flexible, which we accomplish using a novel approach we dubbed stel component analysis. Experimental results show how stel component analysis can assist in image/video segmentation and object recognition where, in particular, it can be used as an alternative of, or in conjunction with, bag-of-features and related classifiers, where stel inference provides a meaningful spatial partition of features.

Hybrid, generative-discriminative, techniques have proven to be valuable approaches in tackling difficult object or scene recognition problems. In general, a generative model over the available data for each image class is first learned providing a relatively comprehensive statistical multi-level representation. In this way, new meaningful image features become available, which encode the degree of fitness of the data with respect to the model at different representation levels. Such features are then fed into a discriminative classifier which can exploit the intrinsic data separability. In this paper, we propose the use of variational free energy terms as feature vectors, so that the degree of fitness of the data and the uncertainty over the generative process are explicitly included in the data description. The proposed method is automatically superior to a pure generative classification, and we also experimentally validate it on a wide selection of generative models applied to challenging benchmarks in hard computer vision tasks such as scene, object, and shape recognition. In several instances, the proposed approach outperforms the current state-of-the-art techniques as for classification results, while also showing to be computationally inexpensive.

We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, variational methods), we solve the inverse problem and locally segment the foreground from the background, estimate the nonuniform motion of each, and fill in the disocclusions. To illustrate the usefulness of both the representation and the estimation algorithm, we show results on stabilization and frame interpolation that are obtained by generating from the trained models.

We propose a technique for automatically learning layers of "flexible sprites" (probabilistic 2-dimensional appearance maps and masks of moving, occluding objects). The model explains each input image as a layered composition of flexible sprites. A variational expectation maximization algorithm is used to learn a mixture of sprites from a video sequence. For each input image, probabilistic inference is used to infer the sprite class, translation, mask values and pixel intensities (including obstructed pixels) in each layer. Exact inference is intractable, but we show how a variational inference technique can be used to process 320/spl times/240 images at 1 frame/second. The only inputs to the learning algorithm are the video sequence, the number of layers and the number of flexible sprites. We give results on several tasks, including summarizing a video sequence with sprites, point-and-click video stabilization, and point-and-click object removal.

In this video we present a new model of interaction for indexing and visualizing video in the context of security applications. We present a method of indexing video by arranging irregularly shaped icons or sprites into a montage representing motion events or security events within the original video scene. The sprites in the montage are used as an index into the original video. We also generate video montages to summarize video in which motion events are compressed and overlayed in a video of shorter time duration. This summary video also acts as an index into the original video stream. We use a simple, novel method of extracting sprites for the image and video montages based on incrementally building a Gaussian mixture model with conjugate priors for the background. We then use fast morphological operators to extract foreground elements. Our approach can be viewed as a fast maximum a posteriori (MAP) inference procedure in a layered image model. The contributions of this work are new interaction and summary schemes that allow viewers to potentially survey hours of security video in the order of minutes.

We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (learning object classes with unsupervised segmentation) which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and pose. A key aspect of this model is that the object appearance is allowed to vary from image to image, allowing for significant within-class variation. By iteratively updating the belief in the object's position, size, segmentation and pose, LOCUS avoids making hard decisions about any of these quantities and so allows for each to be refined at any stage. We show that LOCUS successfully learns an object class model from unlabeled images, whilst also giving segmentation accuracies that rival existing supervised methods. Finally, we demonstrate simultaneous recognition and segmentation in novel images using the learned models for a number of object classes, as well as unsupervised object discovery and tracking in video.

Methods for expanding the dynamic range of digital photographs by combining images taken at different exposures have recently received a lot of attention. Current techniques assume that the photometric transfer function of a given camera is the same (modulo an overall exposure change) for all the input images. Unfortunately, this is rarely the case with today's camera, which may perform complex nonlinear color and intensity transforms on each picture. In this paper, we show how the use of probability models for the imaging system and weak prior models for the response functions enable us to estimate a different function for each image using only pixel intensity values. Our approach also allows us to characterize the uncertainty inherent in each pixel measurement. We can therefore produce statistically optimal estimates for the hidden variables in our model representing scene irradiance. We present results using this method to statistically characterize camera imaging functions and construct high-quality high dynamic range (HDR) images using only image pixel information.

Perceiving sounds in a noisy environment is a challenging problem. Visual lip-reading can provide relevant information but is also challenging because lips are moving and a tracker must deal with a variety of conditions. Typically audio-visual systems have been assembled from individually engineered modules. We propose to fuse audio and video in a probabilistic generative model that implements cross-model self-supervised learning, enabling adaptation to audio-visual data. The video model features a Gaussian mixture model embedded in a linear subspace of a sprite which translates in the video. The system can learn to detect and enhance speech in noise given only a short (30 second) sequence of audio-visual data. We show some results for speech detection and enhancement, and discuss extensions to the model that are under investigation.

In this paper, we present a statistical generative model of scenes with multiple objects that can be efficiently used for tasks related to video search, browsing and retrieval. Instead of using a combination of weighted Euclidean distances as a shot similarity measure, we base the retrieval process on the likelihood of a video frame under the generative model trained on the query sequence. This allows for automatic separation and balancing of various causes of variability, such as occlusion, appearance change and motion. In previous work, this usually required complex user intervention. The likelihood models we study in this paper are based on appearances of multiple, possibly occluding objects in a video clip. Given a query, the video is played at a higher rate until similar frames are found. The playback speed is linked to the frame likelihood, so that the speed drops as the likely target frames are starting to come in.

In this paper we present a method for 3-D reconstruction of human bodies with application in CAD systems for garment design. The reconstruction scheme uses image information from several arbitrary views and deformable superquadrics as the models of the body parts. Two visual cues are used: occluding contours and stereo (possibly aided by projected patterns). Our preliminary experiments show that the reconstruction is more complete than in purely stereo or structured light based methods and more precise than the reconstruction from occluding contours only. From the reconstructed human body, the body measurements can be taken automatically, and used in garment design. We give an example of draping of virtual garment over the photo-realistic 3D model of the imaged human. One can easily envision the use of the described algorithms in the development of custom-fit garment retail software over the Internet, which would include the possibility of trying the garment on in virtual reality.

We describe a real-time system for detecting pointing gestures and estimating the direction of pointing using stereo cameras. Previously, similar systems were implemented using color-based blob trackers, which relied on effective skin color detection; this approach is sensitive to lighting changes and the clothing worn by the user. In contrast, we used a stereo system that produces dense disparity maps in real-time. Disparity maps are considerably less sensitive to lighting changes. Our system subtracts the background, analyzes the foreground pixels to break the body into parts using a robust mixture model, and estimates the direction of pointing. We have tested the system on both coarse and fine pointing by selecting the targets in a room and controlling the cursor on a wall screen, respectively.

We present a self-calibrating algorithm for audio-visual tracking using two microphones and a camera. The algorithm uses a parametrized statistical model which combines simple models of video and audio. Using unobserved variables, the model describes the process that generates the observed data. Hence, it is able to capture and exploit the statistical structure of the audio and video data, as well as their mutual dependencies, The model parameters are estimated by the EM algorithm; object templates are learned and automatic calibration is performed as part of this procedure. Tracking is done by Bayesian inference of the object location using the model. Successful performance is demonstrated on real multimedia clips.

We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it by developing a new algorithm for tracking a moving object in a cluttered, noisy scene using two microphones and a camera. Our model uses unobserved variables to describe the data in terms of the process that generates them. It is therefore able to capture and exploit the statistical structure of the audio and video data separately, as well as their mutual dependencies. Model parameters are learned from data via an EM algorithm, and automatic calibration is performed as part of this procedure. Tracking is done by Bayesian inference of the object location from data. We demonstrate successful performance on multimedia clips captured in real world scenarios using off-the-shelf equipment.

This paper introduces a novel probabilistic model for representing objects that change in appearance as a result of changes in pose, due to small deformations of their sub-parts and the relative spatial transformation of sub-parts of the object. We call the model a probabilistic montage. The model is based upon the idea that an image can be represented as a montage using many, small transformed and cropped patches from a collection of latent images. The approach is similar to that which might be employed by a police artist who might represent an image of a criminal suspect's face using a montage of face parts cut out of a "library" of face parts. In contrast, for our model, we learn the library of small latent images from a set of examples of objects that are changing in shape. In our approach, first the image is divided into a grid of sub-images. Each sub-image in the grid acts as window that crops a piece out of one of a collection of slightly larger images possible for that location in the image. We illustrate various probability models that can be used to encode the appropriate relationships for latent images and cropping transformations among the different patches. In this paper we present the complete algorithm for a tree-structured model. We show how the approach and model are able to find representations of the appearance of full body images of people in motion. We show how our approach can be used to learn representations of objects in an "unsupervised" manner and present results using our model for recognition and tracking purposes in a "supervised" manner.

In this chapter we present techniques for building dressed human models from images. We combine computer vision based approaches such as 3-D reconstruction of a human body and analysis-by-synthesis of the behavior of cloth material with the computer graphics approaches for realistic rendering of complex objects. The experimental results include building textured 3-D models of humans from multiple images, dressing these models into virtual garment, and joint estimation of cloth draping parameters and the underlying object’s geometry in range images of dressed objects.

In this paper, we present an algorithm for real-time tracking of articulated structures in dense disparity maps derived from stereo image sequences. A statistical image formation model that accounts for occlusions plays the central role in our tracking approach. This graphical model (a Bayesian network) assumes that the range image of each part of the structure is formed by drawing the depth candidates from a 3-D Gaussian distribution. The advantage over the classical mixture of Gaussians is that our model takes into account occlusions by picking the minimum depth (which could be regarded as a probabilistic version of z-buffering). The model also enforces articulation constraints among the parts of the structure. The tracking problem is formulated as an inference problem in the image formation model. This model can be extended and used for other tasks in addition to the one described in the paper and can also be used for estimating probability distribution functions instead of the ML estimates of the tracked parameters. For the purposes of real-time tracking, we used certain approximations in the inference process, which resulted in a real-time two-stage inference algorithm. We were able to successfully track upper human body motion in real time and in the presence of self-occlusions.

In this paper we present a method for reconstruction of multipart objects from several arbitrary views using deformable superquadrics as the models of the object's parts. Two visual cues are used: occluding contours and stereo (possibly aided by projected patterns). The object can be relatively complex and can exhibit numerous self occlusions from some or all views. Our preliminary experiments on a human body and a tailor's mannequin show that the reconstruction is more complete than in purely stereo or structured light based methods and more precise than the reconstruction from occluding contours only.