Simultaneous sensing, readout, and classification on an intensity‐ranking image sensor

Ahlberg, Jörgen; Åström, Anders; Forchheimer, Robert

doi:10.1002/cta.2549

Cited by 3 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ahlberg et al present an application‐specific architecture of image sensor in the article entitled “Simultaneous Sensing, Read‐Out, and Classification on an Intensity‐Ranking Image Sensor.” The authors exploit the concept of address‐event representation to perform pixel intensity ranking feeding subsequent image classification. Low computational load and reduced memory are the main advantages of this approach versus others like classification based on state‐of‐the‐art convolutional neural networks.…”

Section: Computational Image Sensorsmentioning

confidence: 99%

Guest editorial: Special issue on computational image sensors and smart camera hardware

Fernández-Berni

Carmona-Galán

Sicard

et al. 2018

Circuit Theory & Apps

View full text Add to dashboard Cite

Section: Computational Image Sensorsmentioning

confidence: 99%

Guest editorial: Special issue on computational image sensors and smart camera hardware

Fernández-Berni

Carmona-Galán

Sicard

et al. 2018

Circuit Theory & Apps

View full text Add to dashboard Cite

“…As one of the classical problems in computer vision, object detection is well‐studied. However, when designing object detection algorithms for embedded systems, complexity of architecture, model size, and effectiveness all should be taken into consideration, 3,4 because of scarce computing and memory resources.…”

Section: Introductionmentioning

confidence: 99%

Lightweight network and parallel computing for fast pedestrian detection

Men

Chen

2020

Circuit Theory & Apps

View full text Add to dashboard Cite

Summary In recent years, researchers have made great efforts in computer vision task (e.g., object detection) with the widely use of convolutional neural networks (CNNs). However, object detection algorithms based on CNNs suffer from high computation cost even on the high‐performance computers. In addition, with the development of high‐resolution videos, the deployment of object detection algorithms becomes more and more difficult because of the large amount of data, let alone the portable platforms, such as unmanned aerial vehicles (UAVs). In this paper, we research a lightweight network on portable platform for outdoor tiny pedestrian detection. Concretely, we first set up a training dataset manually for lack of tiny pedestrian samples in common datasets. We provide a lightweight network, and then, parallel computing is introduced to make the most of the advantage of GPU. Finally, our method can achieve real‐time performance on Jetson TX2. Experimental results verify that the proposed model has promising performance in tiny pedestrian detection designed for portable GPU platforms.

show abstract

Design of classifiers based on ANN approximations of traditional methods

Kruglyak

Forchheimer

2021

Circuit Theory & Apps

View full text Add to dashboard Cite

In this paper, we suggest basing the development of classification methods on traditional techniques but approximating them in whole or in part with artificial neural networks (ANNs). Compared to a direct ANN approach, the underlying traditional method is often easier to analyse. Classification failures can be better understood and corrected for, while at the same time faster execution can be obtained due to the parallel ANN structure. Furthermore, such a two‐step design philosophy partly eliminates the ‘guesswork’ associated with the design of ANNs. The expected gain is thus that the benefits from the traditional field, and the ANN field can be obtained by combining the best features from both fields. We illustrate our approach by working through an explicit example, namely, a Nearest Neighbour classifier applied to a subset of the MNIST database of handwritten digits. Two different approaches are discussed for how to translate the traditional method into an ANN. The first approach is based on a constructive implementation which directly reflects the original algorithm. The second approach uses ANNs to approximate the whole, or part of, the original method. An important part of the approach is to show how improvements can be introduced. In line with the presented philosophy, this is done by extending the traditional method in several ways followed by ANN approximation of the modified algorithms. The extensions are based on a windowed version of the nearest neighbour algorithm. We show that the improvements carry over to the ANN implementations. We further investigate the stability of the solutions by modifying the training set. It is shown that the errors do not change significantly. This also holds true for the ANN approximations providing confidence that the two‐step strategy is robust.

show abstract

Simultaneous sensing, readout, and classification on an intensity‐ranking image sensor

Cited by 3 publications

References 21 publications

Guest editorial: Special issue on computational image sensors and smart camera hardware

Guest editorial: Special issue on computational image sensors and smart camera hardware

Lightweight network and parallel computing for fast pedestrian detection

Design of classifiers based on ANN approximations of traditional methods

Contact Info

Product

Resources

About