We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

/pdf/histograms-of-oriented-gradients-for-human-detection-3nteinziuq.pdf

Histograms of oriented gradients for human detection

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.

/pdf/rapid-object-detection-using-a-boosted-cascade-of-simple-4crej3dxmd.pdf

Rapid object detection using a boosted cascade of simple features

The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection.

This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.

/pdf/the-pascal-visual-object-classes-voc-challenge-ugvl0p2h51.pdf

The Pascal Visual Object Classes (VOC) Challenge

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn.

Fast R-CNN

Grammars are a powerful technique for modeling and extracting the structure of documents. One large challenge, however, is computational complexity. The computational cost of grammatical parsing is related to both the complexity of the input and the ambiguity of the grammar. For programming languages, where the terminals appear in a linear sequence and the grammar is unambiguous, parsing is O(N). For natural languages, which are linear yet have an ambiguous grammar, parsing is O(N/sup 3/). For documents, where the terminals are arranged in two dimensions and the grammar is ambiguous, parsing time can be exponential in the number of terminals. In this paper we introduce (and unify) several types of geometrical data structures which can be used to significantly accelerate parsing time. Each data structure embodies a different geometrical constraint on the set of possible valid parses. These data structures are very general, in that they can be used by any type of grammatical model, and a wide variety of document understanding tasks, to limit the set of hypotheses examined and tested. Assuming a clean design for the parsing software, the same parsing framework can be tested with various geometric constraints to determine the most effective combination.

/pdf/efficient-geometric-algorithms-for-parsing-in-two-dimensions-5df9vuokkg.pdf

Efficient geometric algorithms for parsing in two dimensions

Distributed computing devices comprising a system for sharing computing resources can provide shared computing resources to users having sufficient resource credits. A user can earn resource credits by reliably offering a computing resource for sharing for a predetermined amount of time. The conversion rate between the amount of credits awarded, and the computing resources provided by a user can be varied to maintain balance within the system, and to foster beneficial user behavior. Once earned, the credits can be used to fund the user's account, joint accounts which include the user and others, or others' accounts that do not provide any access to the user. Computing resources can be exchanged on a peer-to-peer basis, though a centralized mechanism can link relevant peers together. To verify integrity, and protect against maliciousness, offered resources can be periodically tested.

Credit-based peer-to-peer storage

A system and method for determining hierarchical information is described. Aspects include using the Collins model for parsing non-textual information into hierarchical content. The system and process assign labels to lines that indicate how the lines relate to one another.

Parsing hierarchical lists and outlines

In previous work we have developed a methodology for texture recognition and synthesis that estimates and exploitsthe dependencies across scale that occur within images."2 In this paper we discuss the application of this techniqueto synthetic aperture radar (SAR) vehicle classification. Our approach measures characteristic cross-scale depen-dencies in training imagery; targets are recognized when these characteristic dependencies are detected. We presentclassification results over a large public database containing SAR images of vehicles. Classification performance iscompared to the Wright Patterson baseline classifier.3 These preliminary experiments indicate that this approachhas sufficient discrimination power to perform target detection/classification in SAR. 1. INTRODUCTION The detection and classification of targets in imagery is a difficult problem. Any successful algorithm must be ableto correctly classify the very wide range of images generated by a single target class. The sources of image variationsin SAR are many: target rotation, translation, articulation, sensor noise, depression angle, overlay, camouflage,and many others. Typically classifiers attempt to deal with these variations in one of two ways: invariance andduplication. For example, translation invariance could be achieved by only measuring the distance between detectedscatters, since distance is invariant to translation. However, such a method does not work as well as the targetrotates, since scatters may appear and then disappear. Alternatively, a duplicative technique could be used at the

/pdf/flexible-histograms-a-multiresolution-target-discrimination-27cxlcnzlo.pdf

Flexible histograms: a multiresolution target discrimination model

We discuss an information theoretic approach for categorizing and modeling dynamic processes. The approach can learn a compact and informative statistic which summarizes past states to predict future observations. Furthermore, the uncertainty of the prediction is characterized nonparametrically by a joint density over the learned statistic and present observation. We discuss the application of the technique to both noise driven dynamical systems and random processes sampled from a density which is conditioned on the past. In the first case we show results in which both the dynamics of random walk and the statistics of the driving noise are captured. In the second case we present results in which a summarizing statistic is learned on noisy random telegraph waves with differing dependencies on past states. In both cases the algorithm yields a principled approach for discriminating processes with differing dynamics and/or dependencies. The method is grounded in ideas from information theory and nonparametric statistics.

/pdf/learning-informative-statistics-a-nonparametnic-approach-3qkikrudh0.pdf

Paul A. Viola

Papers

Efficient geometric algorithms for parsing in two dimensions

Credit-based peer-to-peer storage

Parsing hierarchical lists and outlines

Flexible histograms: a multiresolution target discrimination model

Learning Informative Statistics: A Nonparametnic Approach