A Review of Lightweight Object Detection Algorithms for Mobile Augmented Reality

Nafea, Mohammed Mansoor; Tan, Siok Yee; Jubair, Mohammed Ahmed; Tareq, Mustafa

doi:10.14569/ijacsa.2022.0131162

Cited by 3 publications

(3 citation statements)

References 57 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the region proposal-free approach introduces an important innovation by treating object detection as a direct-regression problem or keypoint prediction [ 35 , 36 , 37 , 38 ]. As real-world applications increasingly require real-time processing [ 39 , 40 , 41 , 42 , 43 ], the importance of region proposal-free detectors such as the proposed PF-FCN becomes more remarkable. In summary, from region proposal-based detectors to region proposal-free detectors, the research emphasis is always on achieving a delicate balance between accuracy and efficiency.…”

Section: Related Workmentioning

confidence: 99%

Proposal-Free Fully Convolutional Network: Object Detection Based on a Box Map

Su,

Adam,

Nasrudin

et al. 2024

Sensors

View full text Add to dashboard Cite

Region proposal-based detectors, such as Region-Convolutional Neural Networks (R-CNNs), Fast R-CNNs, Faster R-CNNs, and Region-Based Fully Convolutional Networks (R-FCNs), employ a two-stage process involving region proposal generation followed by classification. This approach is effective but computationally intensive and typically slower than proposal-free methods. Therefore, region proposal-free detectors are becoming popular to balance accuracy and speed. This paper proposes a proposal-free, fully convolutional network (PF-FCN) that outperforms other state-of-the-art, proposal-free methods. Unlike traditional region proposal-free methods, PF-FCN can generate a “box map” based on regression training techniques. This box map comprises a set of vectors, each designed to produce bounding boxes corresponding to the positions of objects in the input image. The channel and spatial contextualized sub-network are further designed to learn a “box map”. In comparison to renowned proposal-free detectors such as CornerNet, CenterNet, and You Look Only Once (YOLO), PF-FCN utilizes a fully convolutional, single-pass method. By reducing the need for fully connected layers and filtering center points, the method considerably reduces the number of trained parameters and optimizes the scalability across varying input sizes. Evaluations of benchmark datasets suggest the effectiveness of PF-FCN: the proposed model achieved an mAP of 89.6% on PASCAL VOC 2012 and 71.7% on MS COCO, which are higher than those of the baseline Fully Convolutional One-Stage Detector (FCOS) and other classical proposal-free detectors. The results prove the significance of proposal-free detectors in both practical applications and future research.

show abstract

Section: Related Workmentioning

confidence: 99%

Proposal-Free Fully Convolutional Network: Object Detection Based on a Box Map

Su,

Adam,

Nasrudin

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Finally, we discuss the possible uses of these automata in the development design of hardware-and softwarebased stream ciphers. Stream ciphers could continue to play an important role in constrained IoT application where high throughput remains critical and resources are very restricted [14].…”

Section: Introductionmentioning

confidence: 99%

Design and Analysis of a new Stream Cipher based on Ring FCSR Automaton

Gundaram¹,

Tentu²,

Guntupalli³

et al. 2023

IJCDS

View full text Add to dashboard Cite

Feedback with Carry Shift Registers (FCSRs) are being most commonly used in the design of new stream ciphers. This is because the FCSRs have resistance to correlation and algebraic attacks because of their quadratic feedback [1], [2]. Two representations of FCSRs, namely, Galois and Fibonacci are quite popular. However, stream cipher designed using any of these representations is vulnerable to many attacks as proposed in [3], [4]. A new representation called the ring representation, which generalizes and avoids the weaknesses of both the representations of FCSRs has been proposed in [5]. Similar to other representations, the ring representations produce sequences that have high periods and entropy. The advantage of ring representation is that it results in faster diffusion and reduced implementation costs when compared to Galois and Fibonacci. This paper presents two designs of stream cipher based on ring representations. In both algorithms, the output is produced by linear filters that pass randomness tests. The ciphers proposed have undergone a thorough security analysis.

show abstract

“…Convolutional neural networks (CNNs) are built specifically to handle images in the form of multiple arrays. In terms of accuracy, flexibility, and rapid processing, CNNs perform better than conventional methods [9]. The classic CNN architecture uses multiple convolution and pooling operations to extract useful features from images before being passed to the fully connected layers.…”

Section: Introductionmentioning

confidence: 99%

Attention-Based Semantic Segmentation Networks for Forest Applications

Lim,

Zulkifley,

Saleh

et al. 2023

Forests

View full text Add to dashboard Cite

Deforestation remains one of the key concerning activities around the world due to commodity-driven extraction, agricultural land expansion, and urbanization. The effective and efficient monitoring of national forests using remote sensing technology is important for the early detection and mitigation of deforestation activities. Deep learning techniques have been vastly researched and applied to various remote sensing tasks, whereby fully convolutional neural networks have been commonly studied with various input band combinations for satellite imagery applications, but very little research has focused on deep networks with high-resolution representations, such as HRNet. In this study, an optimal semantic segmentation architecture based on high-resolution feature maps and an attention mechanism is proposed to label each pixel of the satellite imagery input for forest identification. The selected study areas are located in Malaysian rainforests, sampled from 2016, 2018, and 2020, downloaded using Google Earth Pro. Only a two-class problem is considered for this study, which is to classify each pixel either as forest or non-forest. HRNet is chosen as the baseline architecture, in which the hyperparameters are optimized before being embedded with an attention mechanism to help the model to focus on more critical features that are related to the forest. Several variants of the proposed methods are validated on 6120 sliced images, whereby the best performance reaches 85.58% for the mean intersection over union and 92.24% for accuracy. The benchmarking analysis also reveals that the attention-embedded high-resolution architecture outperforms U-Net, SegNet, and FC-DenseNet for both performance metrics. A qualitative analysis between the baseline and attention-based models also shows that fewer false classifications and cleaner prediction outputs can be observed in identifying the forest areas.

show abstract

A Review of Lightweight Object Detection Algorithms for Mobile Augmented Reality

Cited by 3 publications

References 57 publications

Proposal-Free Fully Convolutional Network: Object Detection Based on a Box Map

Proposal-Free Fully Convolutional Network: Object Detection Based on a Box Map

Design and Analysis of a new Stream Cipher based on Ring FCSR Automaton

Attention-Based Semantic Segmentation Networks for Forest Applications

Contact Info

Product

Resources

About