Large-Scale Real-Time Object Identification Based on Analytic Features

Hasler, Stephan; Wersing, Heiko; Kirstein, Stephan; Körner, Edgar

doi:10.1007/978-3-642-04277-5_67

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To maintain specificity, it is desirable to have a small sub-sampling factor. This structure is commonly seen in mammalian visual cortex and relevant models (Geismann and Schneider G., 2008;Akbari and Rezaei, 2009;Hasler et al, 2009). According to the latest findings in auditory neuroscience, similar structures have been discovered in the auditory cortex of a number of animals (Pfister et al, 2015;Yeung et al, 2005;Shamma, 2013;Huang et al, 2017).…”

Section: Convnetmentioning

confidence: 64%

Convolutional Neural Network and the Recognition of Vehicle Types

2018

View full text Add to dashboard Cite

In machine learning, a convolutional neural network (ConvNet) is a class of deep, feed-forward artificial neural networks. Featured by low computing load and fast convergence, the network has been successfully applied to pattern recognition. This paper gives a detailed introduction to the structure, working principles and advantages of ConvNet, and applies it to the recognition of vehicle types. In reference to previous research, two deep neural networks were created, namely VGG 16 and AlexNet. The experimental results show that our methods have performed well in vehicle classification in complex background images.

show abstract

Section: Convnetmentioning

confidence: 64%

Convolutional Neural Network and the Recognition of Vehicle Types

2018

View full text Add to dashboard Cite

show abstract

“…After this, a local maximum operation is performed to increase robustness against small translations. This is in contrast to [17], where for an identification task the global maximum per feature was determined. Finally, on top of the hierarchy a single layer perceptron (SLP) is used in a convolutive manner to generate the car response map.…”

Section: B Car Detectionmentioning

confidence: 99%

“…For the detection the gray-scale image is projected to the analytic feature representation proposed in [17]. This feature hierarchy first calculates SIFT descriptors on a regular grid.…”

Section: B Car Detectionmentioning

confidence: 99%

An integrated ADAS for assessing risky situations in urban driving

Weisswange

Bolder

Fritsch

et al. 2013

2013 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

Advanced Driver Assistance Systems (ADAS) are becoming more and more popular. Many of these systems though are limited to specific scenes and often detect risky situations very late so they can only mitigate accidents. These effects are mainly caused by the use of simple physical prediction methods, e.g. to estimate the time-to-contact with another vehicle. In this paper we show an ADAS that extends the functionality of physical collision warnings by additionally estimating potential risks based on implicit predictions. As an example we demonstrate the use of vehicle orientation information for classifying situations. Through this, we can in particular assess the risk of static cars, for which physical prediction does not apply, but which can nevertheless easily cause an accident if they start moving into our driving corridor. The proposed system is evaluated online in a test car and is shown to reliably detect classical risky situations as well as those involving static cars.

show abstract

“…Later in (Mairal et al, 2008b) the authors extend (Mairal et al, 2008a) by learning a single shared dictionary and models for different classes mixing both generative and discriminative methods. There have been some attempts to learn invariant middle level representations (Wersing and Körner, 2003;Boureau et al, 2010), while some other works use sparse representation as main ingredient for feed forward architectures (Hasler et al, 2007;Hasler et al, 2009). Most recent works focus on learning general task purposes dictionaries (Mairal et al, 2012) or they look at the pooling stage (Jia et al, 2012) trying to learn the receptive fields that better catch all the im-age statistics.…”

Section: Introductionmentioning

confidence: 99%

Multi-class Image Classification - Sparsity does it Better

Fanello

Metta

Odone

2013

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

It is well assessed that sparse representations improve the overall accuracy and the systems performances of many image classification problems. This paper deals with the problem of finding sparse and discriminative representations of images in multi-class settings. We propose a new regularized functional, which is a modification of the standard dictionary learning problem, designed to learn one dictionary per class. With this new formulation, while positive examples are constrained to have sparse descriptions, we also consider a contribution from negative examples which are forced to be described in a denser and smoother way. The descriptions we obtain are meaningful for a given class and highly discriminative with respect to other classes, and at the same time they guarantee real-time performances. We also propose a new approach to the classification of single image features which is based on the dictionary response. Thanks to this formulation it is possible to directly classify local features based on their sparsity factor without losing statistical information or spatial configuration and being more robust to clutter and occlusions. We validate the proposed approach in two image classification scenarios, namely single instance object recognition and object categorization. The experiments show the effectiveness in terms of performances and speak in favor of the generality of our method.

show abstract

Large-Scale Real-Time Object Identification Based on Analytic Features

Cited by 8 publications

References 14 publications

Convolutional Neural Network and the Recognition of Vehicle Types

Convolutional Neural Network and the Recognition of Vehicle Types

An integrated ADAS for assessing risky situations in urban driving

Multi-class Image Classification - Sparsity does it Better

Contact Info

Product

Resources

About