Direct inference on compressive measurements using convolutional neural networks

Lohit, Suhas; Kulkarni, Kuldeep; Turaga, Pavan

doi:10.1109/icip.2016.7532691

Cited by 87 publications

(74 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to Refs. [29][30][31], the approach is suitable for stationary camera cases and also the objects are already centered in the images.…”

Section: Compressive Sensingmentioning

confidence: 99%

“…] presents an online reconstruction free approach to object classification using compressed measurements. Similar to [29]- [31] and [35], the approach assumes the object is already at the center of the image. The methods in [29]- [31], [35] and [36] also did not address Instead of using Gaussian random measurements to obtain the compressive measurements, we emphasize that we have proposed two alternative compressive measurements.…”

Section: Compressive Sensingmentioning

confidence: 99%

“…In [29], a convolutional neural network (CNN) approach was presented to perform image classification directly in compressed measurement domain. The input image is assumed to be cropped and centered, and there is only one target in each image.…”

Section: Introductionmentioning

confidence: 99%

“…Papers [30,31] are similar in spirit to [29]. Both papers discussed direct object classification using compressed measurement.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Based Target Tracking and Classification Directly in Compressive Measurement for Low Quality Videos

Kwan¹,

Chou²,

Yang³

et al. 2019

SIPIJ

View full text Add to dashboard Cite

Past research has found that compressive measurements save data storage and bandwidth usage. However, it is also observed that compressive measurements are difficult to be used directly for target tracking and classification without pixel reconstruction. This is because the Gaussian random matrix destroys the target location information in the original video frames. This paper summarizes our research effort on target tracking and classification directly in the compressive measurement domain. We focus on one type of compressive measurement using pixel subsampling. That is, the compressive measurements are obtained by randomly subsample the original pixels in video frames. Even in such special setting, conventional trackers still do not work well. We propose a deep learning approach that integrates YOLO (You Only Look Once) and ResNet (residual network) for target tracking and classification in low quality videos. YOLO is for multiple target detection and ResNet is for target classification. Extensive experiments using optical and mid-wave infrared (MWIR) videos in the SENSIAC database demonstrated the efficacy of the proposed approach.

show abstract

“…Similar to Refs. [29][30][31], the approach is suitable for stationary camera cases and also the objects are already centered in the images.…”

Section: Compressive Sensingmentioning

confidence: 99%

Section: Compressive Sensingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Papers [30,31] are similar in spirit to [29]. Both papers discussed direct object classification using compressed measurement.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Based Target Tracking and Classification Directly in Compressive Measurement for Low Quality Videos

Kwan¹,

Chou²,

Yang³

et al. 2019

SIPIJ

View full text Add to dashboard Cite

show abstract

“…The classification accuracies were greater or equal to 58.94% for compression ratios less than or equal to 98.98%. 20 Classification of compressed data has been shown to maintain high classification accuracies across a wide range of datasets and compression techniques. 21 Removing the requirement to reconstruct an image separates compressive classification from compressive imaging.…”

Section: Introductionmentioning

confidence: 99%

Performance evaluation of two optical architectures for task-specific compressive classification

et al. 2020

View full text Add to dashboard Cite

Many optical systems are used for specific tasks such as classification. Of these systems, the majority are designed to maximize image quality for human observers. However, machine learning classification algorithms do not require the same data representation used by humans. We investigate the compressive optical systems optimized for a specific machine sensing task. Two compressive optical architectures are examined: an array of prisms and neutral density filters where each prism and neutral density filter pair realizes one datum from an optimized compressive sensing matrix, and another architecture using conventional optics to image the aperture onto the detector, a prism array to divide the aperture, and a pixelated attenuation mask in the intermediate image plane. We discuss the design, simulation, and tradeoffs of these systems built for compressed classification of the Modified National Institute of Standards and Technology dataset. Both architectures achieve classification accuracies within 3% of the optimized sensing matrix for compression ranging from 98.85% to 99.87%. The performance of the systems with 98.85% compression were between an F∕2 and F∕4 imaging system in the presence of noise. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Data Driven Sensing for Action Recognition Using Deep Convolutional Neural Networks

Gupta

Anand

Kaushik

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Direct inference on compressive measurements using convolutional neural networks

Cited by 87 publications

References 13 publications

Deep Learning Based Target Tracking and Classification Directly in Compressive Measurement for Low Quality Videos

Deep Learning Based Target Tracking and Classification Directly in Compressive Measurement for Low Quality Videos

Performance evaluation of two optical architectures for task-specific compressive classification

Data Driven Sensing for Action Recognition Using Deep Convolutional Neural Networks

Contact Info

Product

Resources

About