MobileNetV3 With CBAM for Bamboo Stick Counting

Jia, Liangquan; Wang, Yawen; Zang, Ying; Li, Quanfeng; Leng, Huanan; Xiao, Zhanchun; Long, Wei; Jiang, Linhua

doi:10.1109/access.2022.3175818

Cited by 13 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depth-wise separable convolutions employ M × K × K filters that can be represented by a K × K template and M parameters that distribute the template in the depth dimension; this observation has motivated the creation of blueprint-separable convolutions. Every filter kernel F(n) can be depicted using a blueprint B(n) and the weights wn, 1, …, wn, M via F(n)m,:,: = wn, m * B(n) (5) with m in {1, …, M: number of kernels in one filter} and n in {1, …, N: number of filters in one layer}. Figure 13 illustrates the blueprint separable convolutions and their differences from standard convolutions.…”

Section: Blueprint Separable Convolutions To Replace Depth-wise Separ...mentioning

confidence: 99%

“…Our research addresses these limitations by introducing key modifications to the MobileNetV3 architecture tailored for parking lot occupancy detection. This modified version incorporates several architectural improvements, including the use of a Leaky-ReLU6 [3] activation function for the shallow part of the MobileNetV3 model, the replacement of the squeeze-and-excitation module [4] with the convolution block attention module [5], and the replacement of the depth-wise separable convolutions with blueprint separable convolutions [6]. We treat the automatic detection of vacant spaces as a binary classification problem and train and test the improved model on widely used parking management datasets such as CNRPark-EXT [7] and PKLOT [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parking Lot Occupancy Detection with Improved MobileNetV3

Yuldashev,

Mukhiddinov,

Abdusalomov

et al. 2023

Sensors

View full text Add to dashboard Cite

In recent years, parking lot management systems have garnered significant research attention, particularly concerning the application of deep learning techniques. Numerous approaches have emerged for tackling parking lot occupancy challenges using deep learning models. This study contributes to the field by addressing a critical aspect of parking lot management systems: accurate vehicle occupancy determination in specific parking spaces. We propose an advanced solution by harnessing an optimized MobileNetV3 model with custom architectural enhancements, trained on the CNRPark-EXT and PKLOT datasets. The model processes individual parking space patches from real-time video feeds, providing occupancy classification for each patch, identifying occupied or available spaces. Our architectural modifications include the integration of a convolutional block attention mechanism in place of the native attention module and the adoption of blueprint separable convolutions instead of the traditional depth-wise separable convolutions. In terms of performance, our proposed model exhibits superior results when benchmarked against state-of-the-art methods. Achieving an exceptional area under the ROC curve (AUC) value of 0.99 for most experiments with the PKLot dataset, our enhanced MobileNetV3 showcases its exceptional discriminatory power in binary classification. Benchmarked against the CarNet and mAlexNet models, representative of previous state-of-the-art solutions, our proposed model showcases exceptional performance. During evaluations using the combined CNRPark-EXT and PKLot datasets, the proposed model attains an impressive average accuracy of 98.01%, while CarNet achieves 97.03%. Beyond achieving high accuracy and precision comparable to previous models, the proposed model exhibits promise for real-time applications. This work contributes to the advancement of parking lot occupancy detection by offering a robust and efficient solution with implications for urban mobility enhancement and resource optimization.

show abstract

Section: Blueprint Separable Convolutions To Replace Depth-wise Separ...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Parking Lot Occupancy Detection with Improved MobileNetV3

Yuldashev,

Mukhiddinov,

Abdusalomov

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The combined attention mechanism, CBAM (Convolutional Block Attention Module), emerges by integrating these two mechanisms [11] . CBAM attention mechanism achieves better results compared to SENet (Squeeze-and-Excitation Networks) which only focuses on channel attention [12] . The structure of CBAM attention mechanism is shown in Figure 3.…”

Section: Introducing the Cbam Modulementioning

confidence: 99%

A Method of Lightweight Pedestrian Detection in Rainy and Snowy Weather Based on Improved YOLOv5

2024

AJCIS

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technology, pedestrian detection tasks have been widely used in intelligent security and other fields. In rainy and snowy weather, pedestrian detection models may be severely affected, resulting in missed detections and false alarms. This article proposes a lightweight pedestrian detection method based on improved YOLOv5 for rainy and snowy weather conditions. Firstly, to address the issue of insufficient datasets, artificial rain and snow noise is added to the collected pedestrian data. This increases the diversity of the data and improves the robustness of the model in handling pedestrian detection tasks in rainy and snowy weather. Next, a lightweight pedestrian detection model called MAC_YOLOv5s is designed based on the YOLOv5 network model. The MAC_YOLOv5s model replaces the backbone network of the original network with the Mobilenetv3 network to achieve light weight. In addition, the CBAM attention mechanism is integrated to enhance the model's anti-interference ability. The progressive feature pyramid network AFPN is introduced to fuse feature information between adjacent layers, extracting more important features. Experimental results show that the improved MAC_YOLOv5s lightweight pedestrian detection network model reduces the model size to one-third of the original YOLOv5s model, with a file size of only 5.35MB. The mAP value reaches 0.683. These results indicate that the improved MAC_YOLOv5s model has fewer parameters and a smaller model size compared to the original model, making it suitable for pedestrian detection tasks in rainy and snowy weather conditions.

show abstract

“…In multi-vessel/ship detection and classification, the ability to represent the point of interest more accurately is important, and one way to do it is by utilizing attention. A convolutional block attention module (CBAM) [27] is one of the attention networks that has widely been used to improve the detection capabilities in many applications such as fly species recognition [28], bamboo sticks counting [29], safety helmets wear-ing recognition [30], and human activity recognition [31]. Therefore, by leveraging attention mechanisms such as focusing on essential features and suppressing irrelevant ones, we hope to boost the power of representation.…”

Section: Introductionmentioning

confidence: 99%

CRAS-YOLO: A Novel Multi-Category Vessel Detection and Classification Model Based on YOLOv5s Algorithm

2023

View full text Add to dashboard Cite

Multi-category vessel detection and classification based on satellite imagery attract a lot of attention due to their significant applications in the military and civilian domains. In this study, we generated a new Artificial-SAR-Vessel dataset based on the combination of the FUSAR-Ship dataset and the SimpleCopyPaste method. We further proposed a novel multi-category vessel detection called CRAS-YOLO which consisted of a convolutional block attention module (CBAM), receptive fields block (RFB), and adaptively spatial feature fusion (ASFF) based on YOLOv5s. The proposed CRAS-YOLO improved the feature pyramid network based on the path aggregation network (PANet), which integrates the RFB feature enhancement module and ASFF feature fusion strategy to obtain richer feature information and realize the adaptive fusion of multi-scale features (RA-PANet). At the same time, a CBAM is added to the backbone to accurately locate the vessel location and improve detection capability. The results confirmed that the proposed CRAS-YOLO model reached a precision, recall rate, and mean average precision (mAP) (0.5) of up to 90.4%, 88.6%, and 92.1% respectively. The proposed model also outperformed previous studies' results in another Sar Ship Detection (SSDD) dataset with precision, recall, and mAP scores of up to 97.3%, 95.5%, and 98.7% respectively.

show abstract

MobileNetV3 With CBAM for Bamboo Stick Counting

Abstract: Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

Cited by 13 publications

References 26 publications

Parking Lot Occupancy Detection with Improved MobileNetV3

Parking Lot Occupancy Detection with Improved MobileNetV3

A Method of Lightweight Pedestrian Detection in Rainy and Snowy Weather Based on Improved YOLOv5

CRAS-YOLO: A Novel Multi-Category Vessel Detection and Classification Model Based on YOLOv5s Algorithm

Contact Info

Product

Resources

About