Outdoor Scene Classification Research Articles

AWDMC-Net: Classification of Adversarial Weather Degraded Multiclass scenes using a Convolution Neural Network

Computer vision systems in outdoor environments are strongly affected by different atmospheric/weather conditions. Therefore, understanding the actual behavior of outdoor scenes is necessary for effective removal and improvement of the overall performance of computer vision systems. Although the classification of atmospheric/weather conditions has been well explored, reporting on the same in multiclass problem using Convolutional Neural Networks (CNNs) has received very little attention. In response to address this disparity, we propose a new CNN architecture named the “Adversarial Weather Degraded Multi-class scenes Classification Network (AWDMC-Net)” for outdoor scene classification degraded by different atmospheric/weather conditions. The proposed network is based on adopting different combinations of skip connections in building blocks of CNN there after adaptively pruning the least important convolutional kernels from the network. For effective pruning, we proposed a new pruning criterion named “Entropy Guided Mean-l1 Norm” that can adaptively evaluate the importance of convolutional kernels by considering the filters and their corresponding output feature maps. The prediction performance of our proposed model was evaluated on our newly designed E-TUVD (Extended Tripura University Video Dataset) and on publicly available benchmark datasets. Our newly created video dataset, E-TUVD, consists of 147 video clips (approximately 793800 frames) that represent six atmospheric/weather conditions, namely, fog, dust, rain, haze, poor illumination, and clear day conditions. Our proposed model achieves an accuracy of 93.85%, a specificity of 93.79%, and a sensitivity of 94.18% on our dataset, which outperforms the prevailing standard CNN models and recent state-of-the-art methods for atmospheric/weather classification tasks. Furthermore, our network also reduces the time consumption for atmospheric/weather classification tasks, and therefore mostly meets the requirements of practical applications in real-world scenarios.

Classification of 3-D Point Clouds by a New Augmentation Convolutional Neural Network

Nowadays, the classification of point clouds has become a fundamental problem in 3-D information study. Different from the deep learning process of natural images, 3-D point clouds are massive and unorganized, which can be difficultly captured features by the convolution process directly. This letter proposes a new augmentation convolutional neural network (ACNN) to classify point clouds by adding a key augmentation layer before the classical sampling and convolution structure. Input data will be augmented before each sampling layer, which brings abundant learning information to help the network capture more local structures. In order to make the augmentation more effective, we formulate the parameters of augmentation layers learnable in the learning process according to the loss function. The proposed augmentation is based on automatically tuning the magnitude of the smoothness, which plays a significant role in point cloud processing and provides local features, for example, edges, contours, and edges. Results show that we have achieved the overall accuracy of 92.52% and 89.11% in the object classification on ModelNet10 and ModelNet40, respectively, which shows our superiority over other methods. Besides, the ACNN achieves an average miscalculation error of 0.28 and cross-entropy loss of 0.48 in the classification of laser scanning point clouds, which shows high robustness to noise and density in the outdoor scene classification.

An Illumination Estimation Algorithm based on Outdoor Scene Classification

The illumination estimation algorithm belongs to the field of color constancy, aiming to restoring the color of image through estimating the RGB of scene illumination. In different scenarios, the performance of a general algorithm varies greatly. If the scene can be predicted, it can be inferred that the scenarios related optimal algorithms is better than a general algorithm for estimating illumination. In this paper, a novel algorithm based on outdoor scene classification was proposed: firstly, the support vector machine (svm) classifiers was used to identify scene types , and then the scenarios related optimal algorithms was selected, finally used the RGB values of scene illumination were calculated.

Indoor Home Scene Recognition Using Capsule Neural Networks

This paper presents the use of a class of Deep Neural Networks for recognizing indoor home scenes so as to aid Intelligent Assistive Systems (IAS) in performing indoor services to assist elderly or infirm people. Identifying exact indoor location is important so that objects associated with particular tasks can be located speedily and efficiently irrespective of position or orientation. In this way, IAS developed for providing services may become more efficient in accomplishing designated tasks satisfactorily. There are many Convolutional Neural Networks (CNNs) which have been developed for outdoor scene classification and, also, for interior (not necessarily indoor home) scene classification. However, to date, there are no CNNs which are trained, validated and tested on indoor home scene datasets as there appears to be an absence of sufficiently large databases of home scenes.Nonetheless, it is important to train systems which are meant to operate within home environments with the correct relevant data. To counteract this problem, it is proposed that a different type of network is used, which is not very deep (i.e., a network which does not have too many layers) but which can attain sufficiently high classification accuracy using smaller training datasets. A type of neural network likely to help achieve this is a Capsule Neural Network (CapsNet). In this paper, 20,000 indoor home scenes were used for training the CapsNet, and 5000 images were used for testing it. The validation accuracy achieved is 71% and testing accuracy achieved is 70%.

MCCT: a multi-channel complementary census transform for image classification

Census transformation and its variants have gained popularity in image classification for their simplicity and better performance. To describe a texture pattern, these approaches generally use sign information while comparing neighboring pixels. However, our observation is that sign and magnitude in a single color channel as well as in different color channels hold complementary information where sign component captures texture in an image and the saliency of that texture can be captured by the magnitude component. Considering these issues, a multi-channel complementary census transform (MCCT) is proposed in this paper by combining all of these information to capture more discriminating features. Rigorous experiments on nine different datasets which belong to six different applications such as flower, gender, aerial orthoimagery, event, leaf, indoor and outdoor scene classification demonstrate that MCCT outperforms existing state-of-the-art techniques.

Indoor and Outdoor Scene Classification Method Based on Fourier Transform

In this paper, a method for indoor and outdoor scene classification is proposed based on the spectrum information of Fourier transform. Firstly, the image is divided into five partitions. The color, texture, and spectral information of each partition are extracted as feature vector. Each partition has a separate image feature vectors, so the image can be represented by this set of features. For the feature extraction stage, frequency information can be used to classify indoor and outdoor scene. Compared with other classification methods, classification accuracy of this method increased from 91% to 92%, experimental results show that the proposed method is effective.

Biologically Motivated Model for Outdoor Scene Classification

This paper focuses on the problem of scene classification for mobile robots in an outdoor environment. We present a novel model that combines biologically inspired features and cortex-like memory patterns. The biologically inspired gist feature is used to characterize the content of a scene image. The Incremental Hierarchical Discriminant Regression tree is used to simulate the generation and recall process of human memory. The association between the gist feature and the scene label is established in an incremental way. A cognitive model of the world is constructed using real-time online learning, and a new scene differentiated by reasoning. Using the biologically motivated model, we solved the outdoor scene classification problem on the University of Southern California data set. Experimental results indicate the incremental model improves the classification accuracy rates to nearly 100 % and significantly reduces training costs compared with other biologically inspired feature-based approaches. The new scene classification system achieves state-of-the-art performance.

A Novel Method for Efficient Indoor–Outdoor Image Classification

Most traditional indoor---outdoor scene classification approaches utilize the simple statistics of the low-level features, such as colors, edges, and textures. However, the existence of colors similar to sky or grass often yields the false positives. To cope with this deficiency, we focus on the orientation of low-level features in this paper. First, the image is partitioned into five block regions, whose features are differently weighted in the following classification stage according to the block positions. The edge and color orientation histogram (ECOH) descriptors are defined to represent each block efficiently. Finally, all ECOH values are concatenated to generate the feature vector and fed into the SVM classifier for the indoor---outdoor scene classification. To justify the efficiency and robustness of the proposed method, the evaluation is conducted over 1200 images.

Indoor versus Outdoor Scene Classification Using Probabilistic Neural Network

We propose a method for indoor versus outdoor scene classification using a probabilistic neural network (PNN). The scene is initially segmented (unsupervised) using fuzzy-means clustering (FCM) and features based on color, texture, and shape are extracted from each of the image segments. The image is thus represented by a feature set, with a separate feature vector for each image segment. As the number of segments differs from one scene to another, the feature set representation of the scene is of varying dimension. Therefore a modified PNN is used for classifying the variable dimension feature sets. The proposed technique is evaluated on two databases: IITM-SCID2 (scene classification image database) and that used by Payne and Singh in 2005. The performance of different feature combinations is compared using the modified PNN.

Image Transform Bootstrapping and Its Applications to Semantic Scene Classification

The performance of an exemplar-based scene classification system depends largely on the size and quality of its set of training exemplars, which can be limited in practice. In addition, in nontrivial data sets, variations in scene content as well as distracting regions may exist in many testing images to prohibit good matches with the exemplars. Various boosting schemes have been proposed in machine learning, focusing on the feature space. We introduce the novel concept of image-transform bootstrapping using transforms in the image space to address such issues. In particular, three major schemes are described for exploiting this concept to augment training, testing, and both. We have successfully applied it to three applications of increasing difficulty: sunset detection, outdoor scene classification, and automatic image orientation detection. It is shown that appropriate transforms and meta-classification methods can be selected to boost performance according to the domain of the problem and the features/classifier used.

Indoor vs. outdoor scene classification in digital photographs

This paper proposes a new technique for the classification of indoor and outdoor images based on edge analysis. Our technique is based on analysing edge straightness in images. We make an original proposal that indoor images have a greater proportion of edges that are straight compared to outdoor images, and use multi-resolution estimates on edge straightness to improve our results. We also consider this method's possible applications in a real-time system. We compare our proposed technique with a number of other approaches that have been published on indoor/outdoor classification of images and convincingly show on a large database that our method generates much higher accuracy.

Outdoor Scene Classification by a Neural Tree-Based Approach

This paper describes a Neural Tree (NT) based system for outdoor scene classification. A new NT classifier with backtracking capabilities is employed at different levels of the system architecture. First, it is used to obtain a rough interpretation of the scene by classifying each image pixel into multiple classes of static background objects, e.g. road, sky, vegetation, or into one generic class representing moving objects, e.g. vehicles, pedestrians. Then it is applied to obtain a more accurate scene interpretation by classifying all detected mobile objects into multiple classes, e.g. cars, lorries, buses, and also estimating their pose. Experiments have been performed on a large set of optical and infrared images. System performances are tested on both clean and noisy data, and comparative studies with other classifiers (i.e. a multi-layer perceptron, a binary decision tree, a standard NT and a bank of neural networks) and with other scene classification methods are carried out.