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

A method for efficiently comparing two trinary logic representations, including the steps of creating a first data structure (a VALUE data structure) representative of a first set of properties; creating a second data structure (a KNOWN data structure) representative of whether the first set of properties is known; creating a third data structure (a TARGET data structure) representative of a target set of properties; creating a fourth data structure (a WANT data structure) representative of whether the target set of properties is wanted; and comparing the first, second, third, and fourth data structures using bit-wise binary operations to determine whether the first set of known properties are wanted as a target set of properties. In exemplary embodiments, the bit-wise binary operations are performed according to the Boolean equation: (not WANT) or (KNOWN and ((TARGET xor VALUE))). Alternatively, the bit-wise binary operation are performed according to the Boolean equation: (not WANT) or (KNOWN and ((TARGET and VALUE) or ((not TARGET) and (not (VALUE))). These data structures may be any size computer word, including 16 and 32-bit words.

Method for comparing two trinary logic representations in the process of customizing radio broadcasting

A method for detects a specific object in an image. An orientation of an arbitrary object with respect to an image plane is determined and one of a plurality orientation and object specific classifiers is selected according to the orientation. The arbitrary object is classified as a specific object with the selected orientation and object specific classifier.

Detecting arbitrarily oriented objects in images

Human beings exhibit rapid learning when presented with a small number of images of a new object. A person can identify an object under a wide variety of visual conditions after having seen only a single example of that object. This ability can be partly explained by the application of previously learned statistical knowledge to a new setting. This thesis presents an approach to acquiring knowledge in one setting and using it in another. Specifically, we develop probability densities over common image changes. Given a single image of a new object and a model of change learned from a different object, we form a model of the new object that can be used for synthesis, classification, and other visual tasks. 
We start by modeling spatial changes. We develop a framework for learning statistical knowledge of spatial transformations in one task and using that knowledge in a new task. By sharing a probability density over spatial transformations learned from a sample of handwritten letters, we develop a handwritten digit classifier that achieves 88.6% accuracy using only a single hand-picked training example from each class. 
The classification scheme includes a new algorithm, congealing , for the joint alignment of a set of images using an entropy minimization criterion. We investigate properties of this algorithm and compare it to other methods of addressing spatial variability in images. We illustrate its application to binary images, gray-scale images, and a set of 3-D neonatal magnetic resonance brain volumes. 
Next, we extend the method of change modeling from spatial transformations to color transformations. By measuring statistically common joint color changes of a scene in an office environment, and then applying standard statistical techniques such as principal components analysis, we develop a probabilistic model of color change. We show that these color changes, which we call color flows, can be shared effectively between certain types of scenes. That is, a probability density over color change developed by observing one scene can provide useful information about the variability of another scene. We demonstrate a variety of applications including image synthesis, image matching, and shadow detection. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

/pdf/learning-from-one-example-in-machine-vision-by-sharing-3or4tuu7xa.pdf

Learning from one example in machine vision by sharing probability densities

A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system. In additional embodiments, combination classifiers are trained using various combinations of weight trimming, bootstrapping, and a weak classifier termed a “fat stump” classifier.

Learning classifiers using combined boosting and weight trimming

We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be used to both derive an object recognition algorithm and an algorithm for learning the features themselves. The overall approach, called complex feature recognition or CFR, is unique for several reasons: it is broadly applicable to a wide range of object types, it makes constructing object models easy, it is capable of identifying either the class or the identity of an object, and it is computationally efficient--requiring time proportional to the size of the image. Instead of a single simple feature such as an edge, CFR uses a large set of complex features that are learned from experience with model objects. The response of a single complex feature contains much more class information than does a single edge. This significantly reduces the number of possible correspondences between the model and the image. In addition, CFR takes advantage of a type of image processing called "oriented energy". Oriented energy is used to efficiently pre-process the image to eliminate some of the difficulties associated with changes in lighting and pose.

Paul A. Viola

Papers

Method for comparing two trinary logic representations in the process of customizing radio broadcasting

Detecting arbitrarily oriented objects in images

Learning from one example in machine vision by sharing probability densities

Learning classifiers using combined boosting and weight trimming

Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects