Unsupervised Feature Learning for RGB-D Based Object Recognition

Bo, Liefeng; Ren, Xiaofeng; Fox, Dieter

doi:10.1007/978-3-319-00065-7_27

Cited by 276 publications

(208 citation statements)

References 35 publications

Supporting

Mentioning

208

Contrasting

Order By: Relevance

“…In the committee above if we only keep mirroring as dataset augmentation, we get 67.39%. Unsupervised feature learning by augmenting single images [6] 67.4 ± 0.6 Efficient Discriminative Convolution Using Fisher Weight Map [12] 66.0 ± 0.7 Unsupervised Feature Learning for RGB-D Based Object Recognition [1] 64.5 ± 1 Discriminative Learning of Sum-Product Networks [8] 62.3 ± 1 Selecting Receptive Fields in Deep Networks [3] 60.1 ± 1 This paper 68.0 ± 0.55…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Committees of Deep Feedforward Networks Trained with Few Data

Miclut

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Deep convolutional neural networks are known to give good results on image classification tasks. In this paper we present a method to improve the classification result by combining multiple such networks in a committee. We adopt the STL-10 dataset which has very few training examples and show that our method can achieve results that are better than the state of the art. The networks are trained layer-wise and no backpropagation is used. We also explore the effects of dataset augmentation by mirroring, rotation, and scaling.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Thus, we disregard the original meaning of the classifier output and scale the set of values to [0, 1] in order to obtain some scores that will be later combined. Now, for an input test image, we have N sets of scores in [0,1]. Each set of scores corresponds to the output of one network.…”

Section: Building the Committeementioning

confidence: 99%

Committees of Deep Feedforward Networks Trained with Few Data

Miclut

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Later on, due to its capability of providing accurate depth information with relatively low cost, the usage of Kinect goes beyond gaming, and is extended to the computer vision field. This device equipped with intelligent algorithms is contributing to various applications, such as 3D-simultaneous localization and mapping (SLAM) [39,54], people tracking [69], object recognition [11] and human activity analysis [13,57], etc. In this section, we introduce Kinect from two perspectives: hardware configuration and software tools.…”

Section: A Brief Review Of Kinectmentioning

confidence: 99%

RGB-D datasets using microsoft kinect or similar sensors: a survey

Cai

Han

Liu

et al. 2016

Multimed Tools Appl

130

View full text Add to dashboard Cite

RGB-D data has turned out to be a very useful representation of an indoor scene for solving fundamental computer vision problems. It takes the advantages of the color image that provides appearance information of an object and also the depth image that is immune to the variations in color, illumination, rotation angle and scale. With the invention of the low-cost Microsoft Kinect sensor, which was initially used for gaming and later became a popular device for computer vision, high quality RGB-D data can be acquired easily. In recent years, more and more RGB-D image/video datasets dedicated to various applications have become available, which are of great importance to benchmark the stateof-the-art. In this paper, we systematically survey popular RGB-D datasets for different applications including object recognition, scene classification, hand gesture recognition, 3D-simultaneous localization and mapping, and pose estimation. We provide the insights into the characteristics of each important dataset, and compare the popularity and the difficulty of those datasets. Overall, the main goal of this survey is to give a comprehensive description about the available RGB-D datasets and thus to guide researchers in the selection of suitable datasets for evaluating their algorithms.

show abstract

“…Feature learning has been applied successfully in computer vision; the technique has achieved state-of-the-art performance in object detection [25], image classification [26] and object recognition [27] tasks. We demonstrate the utility and generality of such a system by using it for automated classification of three invasive weed species on the north-west slopes of New South Wales, Australia.…”

Section: Introductionmentioning

confidence: 99%

Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV

2014

View full text Add to dashboard Cite

The development of low-cost unmanned aerial vehicles (UAVs) and light weight imaging sensors has resulted in significant interest in their use for remote sensing applications. While significant attention has been paid to the collection, calibration, registration and mosaicking of data collected from small UAVs, the interpretation of these data into semantically meaningful information can still be a laborious task. A standard data collection and classification work-flow requires significant manual effort for segment size tuning, feature selection and rule-based classifier design. In this paper, we propose an alternative learning-based approach using feature learning to minimise the manual effort required. We apply this system to the classification of invasive weed species. Small UAVs are suited to this application, as they can collect data at high spatial resolutions, which is essential for the classification of small or localised weed outbreaks. In this paper, we apply feature learning to generate a bank of image filters that allows for the extraction of features that discriminate between the weeds of interest and background objects. These features are pooled to summarise the image statistics and form the input to a texton-based linear classifier that classifies an image patch as weed or background. We evaluated our approach to weed classification on three weeds of significance in Australia: water hyacinth, tropical soda apple and serrated tussock. Our results showed that collecting images at 5-10 m resulted in the highest classifier accuracy, indicated by F1 scores of up to 94%.Remote Sens. 2014, 6 12038

show abstract

Unsupervised Feature Learning for RGB-D Based Object Recognition

Cited by 276 publications

References 35 publications

Committees of Deep Feedforward Networks Trained with Few Data

Committees of Deep Feedforward Networks Trained with Few Data

RGB-D datasets using microsoft kinect or similar sensors: a survey

Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV

Contact Info

Product

Resources

About