Haoyu Ren

Fast object detection using boosted co-occurrence histograms of oriented gradients

Co-occurrence histograms of oriented gradients (CoHOG) are powerful descriptors in object detection. In this paper, we propose to utilize a very large pool of CoHOG features with variable-location and variable-size blocks to capture salient characteristics of the object structure. We consider a CoHOG feature as a block with a special pattern described by the offset. A boosting algorithm is further introduced to select the appropriate locations and offsets to construct an efficient and accurate cascade classifier. Experimental results on public datasets show that our approach simultaneously achieves high accuracy and fast speed on both pedestrian detection and car detection tasks.

Gender Recognition Using Complexity-Aware Local Features

We propose a gender classifier using two types of local features, the gradient features which have strong discrimination capability on local patterns, and the Gabor wavelets which reflect the multi-scale directional information. The Real Ad a Boost algorithm with complexity penalty term is applied to choose meaningful regions from human face for feature extraction, while balancing the discriminative capability and the computation cost at the same time. Linear SVM is further utilized to train a gender classifier based on the selected features for accuracy evaluation. Experimental results show that the proposed approach outperforms the methods using single feature. It also achieves comparable accuracy with the state-of-the-art algorithms on both controlled datasets and real-world datasets.

Age Estimation Based on Complexity-Aware Features

The research related to age estimation using face images has become increasingly important. We propose an age estimator using two kinds of local features, the gradient features which well describe the local characteristic, and the Gabor wavelets which reflect the multi-scale directional information. The RealAdaBoost algorithm with a complexity penalty term in the feature selection module is applied to choose meaningful regions from human face for feature extraction, while balancing the discriminative capability and the computation cost at the same time. Furthermore, the hierarchical classifier, which is composed of an age group classification (e.g., 15–39 years old, 40–59 years old etc.) and a detailed age estimation (e.g. 19, 53 years old, etc.) are utilized to get the final age. Experimental results show that the proposed approach outperforms the methods using single feature on PAL and FG-NET database. It also achieves competitive accuracy with the state-of-the-art algorithms.

Boosted local binaries for object detection

We propose a novel binary feature for object detection encoding local neighbor patterns of different sizes and locations. Each region pair of the proposed feature is selected by RealAdaBoost algorithm with a penalty term on the structure diversity. As a result, useful features that are good at describing specific objects will be chosen to build the classifier. Moreover, the encoding scheme is applied in both the gradient domain and the intensity domain, which is complementary to standard binary features (e.g. LBP and LAB). The proposed method was tested using the CMU-MIT frontal face dataset, INRIA pedestrian dataset, and UIUC car dataset respectively. Experimental results show that the proposed method outperforms traditional binary features LBP and LAB, which contributes to a significant improvement on detection accuracy and converges 2 times faster. It also achieves comparable performance with some state-of-the-art algorithms.

Object Detection Using Generalization and Efficiency Balanced Co-Occurrence Features

In this paper, we propose a high-accuracy object detector based on co-occurrence features. Firstly, we introduce three kinds of local co-occurrence features constructed by the traditional Haar, LBP, and HOG respectively. Then the boosted detectors are learned, where each weak classifier corresponds to a local image region with a co-occurrence feature. In addition, we propose a Generalization and Efficiency Balanced (GEB) framework for boosting training. In the feature selection procedure, the discrimination ability, the generalization power, and the computation cost of the candidate features are all evaluated for decision. As a result, the boosted detector achieves both high accuracy and good efficiency. It also shows performance competitive with the state-of-the-art methods for pedestrian detection and general object detection tasks.

Object detection using edge histogram of oriented gradient

In this paper, we address the object detection problem by a proposed gradient feature, the Edge Histogram of Oriented Gradient (Edge-HOG). Edge-HOG consists of several blocks arranged along a line or an arc, which is designed to describe the edge pattern. In addition, we propose a new feature extraction method, which extracts the structural information based on the gravity centers as complementary to traditional gradient histograms. As a result, the proposed Edge-HOG not only reflects the local shape information of objects, but also captures more significant appearance information. Experimental results show that the proposed approach significantly improves both the detection accuracy and the convergence speed compared to the traditional HOG feature. It also achieves performance competitive with some commonly-used methods on pedestrian detection and car detection tasks.

Strip Features for Fast Object Detection

This paper presents a set of effective and efficient features, namely strip features, for detecting objects in real-scene images. Although shapes of a specific class usually have large intraclass variance, some basic local shape elements are relatively stable. Based on this observation, we propose a set of strip features to describe the appearances of those shape elements. Strip features capture object shapes with edgelike and ridgelike strip patterns, which significantly enrich the efficient features such as Haar-like and edgelet features. The proposed features can be efficiently calculated via two kinds of approaches. Moreover, the proposed features can be extended to a perturbed version (namely, perturbed strip features) to alleviate the misalignment caused by deformations. We utilize strip features for object detection under an improved boosting framework, which adopts a complexity-aware criterion to balance the discriminability and efficiency for feature selection. We evaluate the proposed approach for object detection on the public data sets, and the experimental results show the effectiveness and efficiency of the proposed approach.

Object detection using boosted local binaries

This paper presents a novel binary descriptor Boosted Local Binary (BLB) for object detection. The proposed descriptor encodes variable local neighbour regions in different scales and locations. Each region pair of the proposed descriptor is selected by the RealAdaBoost algorithm with a penalty term on the structural diversity. As a result, confident features that are good at describing specific characteristics will be chosen. Moreover, the encoding scheme is applied in the gradient domain in addition to the intensity domain, which is complementary to standard binary descriptors. The proposed method was tested using three benchmark object detection datasets, the CalTech pedestrian dataset, the FDDB face dataset, and the PASCAL VOC 2007 dataset. Experimental results demonstrate that the detection accuracy of the proposed BLB clearly outperforms traditional binary descriptors. It also achieves comparable performance with some state-of-the-art algorithms. HighlightsPropose a new binary descriptor with variable patterns.Design a structure-aware framework to balance the discriminative ability and generalization power of the proposed descriptor.5% accuracy improvement compared to traditional binary descriptors.Effective for large scale dataset and general object detection task.

Basis mapping based boosting for object detection

We propose a novel mapping method to improve the training accuracy and efficiency of boosted classifiers for object detection. The key step of the proposed method is a non-linear mapping on original samples by referring to the basis samples before feeding into the weak classifiers, where the basis samples correspond to the hard samples in the current training stage. We show that the basis mapping based weak classifier is an approximation of kernel weak classifiers while keeping the same computation cost as linear weak classifiers. As a result, boosting with such weak classifiers is more effective. In this paper, two different non-linear mappings are shown to work well. We adopt the LogitBoost algorithm to train the weak classifiers based on the Histogram of Oriented Gradient descriptor (HOG). Experimental results show that the proposed approach significantly improves the detection accuracy and training efficiency of the boosted classifier. It also achieves high performance on public datasets for both pedestrian detection and general object detection tasks.

Object recognition based on deformable edge set

We aim to solve the object recognition problem by a novel contour feature called Deformable Edge Set (DES). The DES consists of several Deformable Edge Features (DEF), which is deformed from an edge template to the actual object contour according to the distribution model of pixels. Then the DES is constructed based on the combination of DEF, where the arrangement and the deformable parameters are learned in a subspace. The RealAdaBoost algorithm is further utilized to select meaningful DES to localize the object. Experimental results show that the proposed approach not only locates the object bounding boxes but also captures the object contours well. It also achieves performance competitive with the commonly-used algorithms.