Generating Pedestrian Training Dataset using DCGAN

Kim, Daeun Dana; Shahid, Muhammad Tanseef; Kim, Yun-Seong; Lee, Wonjun; Song, Hyun Chul; Piccialli, Francesco; Choi, Kwang Nam

doi:10.1145/3373419.3373458

Cited by 9 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, few have investigated their potential for creating pedestrian training datasets. This research addresses this gap by using DCGAN to generate realistic pedestrian images for training [10].This work describes a vision-based system that uses a bio-inspired Adaptive Boosting algorithm to recognize and track Crownof-Thorns starfish in reef habitats. With great accuracy (>90%) in complicated backgrounds, the model establishes the framework for autonomous robotic control, vital for safeguarding and preserving coral reefs [11].This work describes a vision-based system that uses a bio-inspired Adaptive Boosting algorithm to recognize and track Crownof-Thorns starfish in reef habitats.…”

Section: Related Workmentioning

confidence: 99%

Synthetic Generation and Detection of Crown-of-Thorns Starfish Instances retrival in Underwater Image

Sekar,

mohan

2024

Preprint

View full text Add to dashboard Cite

Crown-of-thorns starfish (COTS), which eats coral is becoming increasingly common. Coral reefs, which are highly valued for their aesthetic appeal and ecological importance, are seriously threatened. This collection of carefully shot underwater photo sequences covering the whole Great Barrier Reef at different times and places is an invaluable resource for understanding and mitigating the negative effects of commercial overfishing (COTS) on these fragile ecosystems. Due to the predatory nature of the crown-of-thorns starfish coral reefs face significant threats necessitating urgent innovation in methods to control their population.

show abstract

Section: Related Workmentioning

confidence: 99%

Synthetic Generation and Detection of Crown-of-Thorns Starfish Instances retrival in Underwater Image

Sekar,

mohan

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The last layer of generative model is activated by tanh instead while the discriminative model is totally activated by Leakly-Relu function. 30 In DCGAN, p data refers to a generating variable about the data x. z is random noise added to the generator G(z) with the real world images. The generative model has relativity to the argument 𝜃 g while the discriminative model D(x) is related to the parameter 𝜃 d .…”

Section: Dcganmentioning

confidence: 99%

Real‐time COVID‐19 detection over chest x‐ray images in edge computing

Chen

Shi

et al. 2022

Computational Intelligence

View full text Add to dashboard Cite

Severe Coronavirus Disease 2019 (COVID‐19) has been a global pandemic which provokes massive devastation to the society, economy, and culture since January 2020. The pandemic demonstrates the inefficiency of superannuated manual detection approaches and inspires novel approaches that detect COVID‐19 by classifying chest x‐ray (CXR) images with deep learning technology. Although a wide range of researches about bran‐new COVID‐19 detection methods that classify CXR images with centralized convolutional neural network (CNN) models have been proposed, the latency, privacy, and cost of information transmission between the data resources and the centralized data center will make the detection inefficient. Hence, in this article, a COVID‐19 detection scheme via CXR images classification with a lightweight CNN model called MobileNet in edge computing is proposed to alleviate the computing pressure of centralized data center and ameliorate detection efficiency. Specifically, the general framework is introduced first to manifest the overall arrangement of the computing and information services ecosystem. Then, an unsupervised model DCGAN is employed to make up for the small scale of data set. Moreover, the implementation of the MobileNet for CXR images classification is presented at great length. The specific distribution strategy of MobileNet models is followed. The extensive evaluations of the experiments demonstrate the efficiency and accuracy of the proposed scheme for detecting COVID‐19 over CXR images in edge computing.

show abstract