Texton Forests Research Articles

Multi-objects Detection and Segmentation for Scene Understanding Based on Texton Forest and Kernel Sliding Perceptron

In the recent days, scene understanding has become hot research topic due to its real usage at perceiving, analyzing and recognizing different dynamic scenes coverage during GPS monitoring system, drone’s targets, auto-driving and tourist guide. The goal of scene understanding is to make machines look at like humans do, which means the accurate recognition of the contents in scenes and during location observations. Then, we perform two operations such as (1) to perfectly describe the whole environment and (2) to describe what action is going on in the environment. Due to complex scene analysis, recognition of multiple objects and the relation between the objects remain as a challenging part of the research. In this paper, we have proposed a novel approach for the scene understanding that integrates multiple objects detection/segmentation and scene labeling using Geometric features, Histogram of oriented gradient and scale invariant feature transform descriptors. The complete procedure of the purposed model includes resizing and noise removing of images from the dataset, multiple object segmentation and detection, feature extraction and multiple object recognition using multi-layer kernel sliding perceptron. After that, scene recognition is achieved by using multi-class logistic regression. Finally, two datasets such as MSRC and UIUC sports are used for the experimental evaluation of our proposed method. Our purposed method accurately handles the complex objects physical exclusion and objects occlusion. Therefore, it outperforms in term of accuracy compared with other state-of-the-art approaches.

Semantic Texton Forests for Image Categorization and Segmentation

Semantic Texton Forests for Image Categorization and Segmentation

A Survey on Semantic Texton Forests for Image Categorization and Segmentation

A Survey on Semantic Texton Forests for Image Categorization and Segmentation

Manifold Embedding and Semantic Segmentation for Intraoperative Guidance With Hyperspectral Brain Imaging.

Recent advances in hyperspectral imaging have made it a promising solution for intra-operative tissue characterization, with the advantages of being non-contact, non-ionizing, and non-invasive. Working with hyperspectral images in vivo, however, is not straightforward as the high dimensionality of the data makes real-time processing challenging. In this paper, a novel dimensionality reduction scheme and a new processing pipeline are introduced to obtain a detailed tumor classification map for intra-operative margin definition during brain surgery. However, existing approaches to dimensionality reduction based on manifold embedding can be time consuming and may not guarantee a consistent result, thus hindering final tissue classification. The proposed framework aims to overcome these problems through a process divided into two steps: dimensionality reduction based on an extension of the T-distributed stochastic neighbor approach is first performed and then a semantic segmentation technique is applied to the embedded results by using a Semantic Texton Forest for tissue classification. Detailed in vivo validation of the proposed method has been performed to demonstrate the potential clinical value of the system.

Automated Detection of Multiple Pavement Defects

AbstractKnowing the pavement condition is essential for efficiently deciding on maintenance programs. Current practice is predominantly manual with only 0.4% of inspections happening automatically. All methods in the literature aiming at automating condition assessment focus on two defects at most, or are too expensive for practical application. In this paper, the authors propose a low-cost method that automatically detects pavement defects simultaneously using parking camera video data. The types of defects addressed in this paper are two types of cracks (longitudinal and transverse), patches, and potholes. The method uses the semantic texton forests (STFs) algorithm as a supervised classifier on a calibrated region of interest (myROI), which is the area of the video frame depicting only the usable part of the pavement lane. It is validated using data collected from the local streets of Cambridge, U.K. Based on the results of multiple experiments, the overall accuracy of the method is above 82%, with a p...

Semantic segmentation of images exploiting DCT based features and random forest

This paper presents an approach for generating class-specific image segmentation. We introduce two novel features that use the quantized data of the Discrete Cosine Transform (DCT) in a Semantic Texton Forest based framework (STF), by combining together colour and texture information for semantic segmentation purpose. The combination of multiple features in a segmentation system is not a straightforward process. The proposed system is designed to exploit complementary features in a computationally efficient manner. Our DCT based features describe complex textures represented in the frequency domain and not just simple textures obtained using differences between intensity of pixels as in the classic STF approach. Differently than existing methods (e.g., filter bank) just a limited amount of resources is required. The proposed method has been tested on two popular databases: CamVid and MSRC-v2. Comparison with respect to recent state-of-the-art methods shows improvement in terms of semantic segmentation accuracy.

Content-Aware Image Retargeting Based on Semantic Analysis

This paper presents a retargeting approach based on semantic analysis. Our approach has better performance in images that have comlicated backgroud or multi-objects. Our aim is to protect important object in retargeting process. So we brought in object recognition and image importance calculation for retargeting. This approach consists of three parts: object recognition, the importance of image calculation and image retargeting. (i) Firstly we optimized semantic texton forest (STF)[11]and got much better results of object recognition.(ii) Secondly we presented a method called dynamically adjust importance image calculation. (iii) Thirdly we give a retargeting method based on triangular mesh. According to importance image we cover Delaunay triangular mesh on image and solve optimization mesh transforming based on energy function which subjects to least energy loss and boundary restraint. Compared with previous approaches, our method has better result in some complex scene images.

Bi-Temporal Texton Forest for Land Cover Transition Detection on Remotely Sensed Imagery

With the advancement of machine learning, classification methods have been increasingly used in change (or transition) detection. The texton forest (TF)-based method has received increasing research attention because of its speed, good generalization characteristics, stability, and especially its ability to capture spatial contextual information. In this paper, we propose a TF-based method for transition detection in remotely sensed imagery. We investigate a maximal joint-information gain criterion for random forests to better capture combined information in the bi-temporal images in transition detection, which is implemented by a natural extension of binary-trees in traditional methods into a quad-decision tree structure. We also utilize color-invariant gradient as a feature to help alleviate the impact of difference in imaging conditions on bi-temporal transition detection. The experimental results for transition detection show that our bi-temporal TF classifier achieves better performance than a post-classification comparison method and several other alternative methods.

Image categorization using a semantic hierarchy model with sparse set of salient regions

Image categorization in massive image database is an important problem. This paper proposes an approach for image categorization, using sparse set of salient semantic information and hierarchy semantic label tree (HSLT) model. First, to provide more critical image semantics, the proposed sparse set of salient regions only at the focuses of visual attention instead of the entire scene was formed by our proposed saliency detection model with incorporating low and high level feature and Shotton's semantic texton forests (STFs) method. Second, we also propose a new HSLT model in terms of the sparse regional semantic information to automatically build a semantic image hierarchy, which explicitly encodes a general to specific image relationship. And last, we archived image dataset using image hierarchical semantic, which is help to improve the performance of image organizing and browsing. Extension experimental results showed that the use of semantic hierarchies as a hierarchical organizing framework provides a better image annotation and organization, improves the accuracy and reduces human's effort.

Segmentation and Recognition of Highway Assets Using Image-Based 3D Point Clouds and Semantic Texton Forests

AbstractEfficient data collection of high-quantity and low-cost highway assets such as road signs, traffic signals, light poles, and guardrails is a critical element to the operation, maintenance, and preservation of transportation infrastructure systems. Despite its importance, current practice of highway asset data collection is time-consuming, subjective, and potentially unsafe. The high volume of the data that needs to be collected can also negatively impact the quality of the analysis. To address these limitations, this paper proposes a new algorithm for semantic segmentation and recognition of highway assets using video frames collected from a car-mounted camera. The proposed set of algorithms (1) takes the captured frames and using a pipeline of structure from motion and multiview stereo reconstructs a three-dimensional (3D) point cloud model of the highway and surrounding assets; (2) using a Semantic Texton Forest classifier, each geo-registered two-dimensional (2D) video frame at the pixel-level ...

A combined method for multi-class image semantic segmentation

Multi-class image semantic segmentation (MCISS) is one of the most crucial steps toward many applications related with consumer electronics fields such as image editing and content-based image retrieval. Existing MCISS approaches often consider only the top-down process and suffer from poor label consistency among neighboring pixels. To overcome this limitation, this paper proposes a combined MCISS method to integrate a state-of-the-art topdown (TD) approach Semantic Texton Forests (STF) and a classical bottom-up (BU) approach JSEG to exploit their relative merits. Experimental results on two challenging datasets show that the proposed method can achieve higher accuracy in comparison with the original STF method, while it does not notably prolong the computational time. In addition, several insights into the evaluation metrics of MCISS are reported.

Rotation-Invariant Object Detection of Remotely Sensed Images Based on Texton Forest and Hough Voting

The Hough forest method is an effective method for object detection in ground-shot images that has received increasing research attention. However, this method lacks the ability to detect objects with arbitrary orientations. This largely constrains the method from being used in detecting geospatial objects from remotely sensed (RS) images since geospatial objects can have many different orientations. In order to achieve rotation invariance and compensate the associated loss of discriminative power, this paper presents a novel color-enhanced rotation-invariant Hough forest (CRIHF) method for detecting geospatial objects in RS images. In our method, we propose to train a Pose-Estimation-based Rotation-invariant Texton Forest (PE-RTF) which first uses dominant gradient orientations to align local image patches. The orientations are then jointly used with coordinates in Hough voting to detect object position. In order to increase discriminative power, Texton Forest is used in codebook generation. Moreover, theoretically sound color-invariant gradients are employed. By rotating split functions rather than image patches in the RTF and sparsely accumulating Hough votes on grid points, computational times can be reduced by two orders of magnitude. The evaluation of the CRIHF method on a data set containing 525 airplanes and a second data set containing 68 residential buildings shows that our method is rotation invariant and robust. The detector achieves around 90% recall rate on both data sets. Experiments also show that our method is noise resistant and can achieve a decent detection performance at a high level (30%) of “salt and pepper” impulsive noise.

Land Cover Classification for Remote Sensing Imagery Using Conditional Texton Forest With Historical Land Cover Map

In this letter, we propose a “conditional texton forest” (CTF) method to utilize widely available historical land cover (HLC) maps in land use/cover classification on high-resolution images. The CTF is based on texton forest (TF), which is a popular and powerful method in image semantic segmentation due to its effective use of spatial contextual information, its high accuracy, and its fast speed in multiclass classification. The proposed CTF method nonparametrically aggregates a bank of TFs according to HLC information and uses the fact that different types of HLC follow different transition rules. The performance of CTF is compared to support vector machine (SVM), Markov random field (MRF), and a naive TF method which uses historical data directly as a feature channel. On average, CTF results in a 2%-5% higher classification accuracy than other classifiers in our experiment. The classifying speed of CTF is similar with TF, five times faster than MRF, and hundreds of times faster than SVM. Given the abundance of HLC data, the proposed method can be expected to be useful in a wide range of socioeconomic and environmental studies.

Image Categorization Using Scene-Context Scale Based on Random Forests

Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective scale of local context to classify an image pixel in a scene. This paper presents random forests based image categorization using the scene-context scale. The proposed method uses random forests, which are ensembles of randomized decision trees. Since the random forests are extremely fast in both training and testing, it is possible to perform classification, clustering and regression in real time. We train multi-scale texton forests which efficiently provide both a hierarchical clustering into semantic textons and local classification in various scale levels. The scene-context scale can be estimated by the entropy of the leaf node in the multi-scale texton forests. For image categorization, we combine the classified category distributions in each scale and the estimated scene-context scale. We evaluate on the MSRC21 segmentation dataset and find that the use of the scene-context scale improves image categorization performance. Our results have outperformed the state-of-the-art in image categorization accuracy.