Comparative analysis of deep learning image detection algorithms

Srivastava, Shrey; Divekar, Amit Vishvas; Anilkumar, Chandu; Naik, Ishika; Kulkarni, Ved; Pattabiraman, V.

doi:10.1186/s40537-021-00434-w

Cited by 197 publications

(77 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The YOLO-V3 network was trained using Google Colab [17], as it has a powerful graphics processing unit and more compute unified device architecture (CUDA) cores to reduce the overall training time [18]. It took around 5 to 6 hours for 2,000 iterations using 1,000 images of the required crop, which is to be detected 19], [20].…”

Section: Proposed Solutionmentioning

confidence: 99%

Agricultural harvesting using integrated robot system

Raja¹,

B²,

Nagaraj³

et al. 2022

IJEECS

View full text Add to dashboard Cite

In today's competitive world, robot designs are developed to simplify and improve quality wherever necessary. The rise in technology and modernization has led people from the unskilled sector to shift to the skilled sector. The agricultural sector's solution for harvesting fruits and vegetables is manual labor and a few other agro bots that are expensive and have various limitations when it comes to harvesting. Although robots present may achieve harvesting, the affordability of such designs may not be possible by small and medium-scale producers. The integrated robot system is designed to solve this problem, and when compared with the existing manual methods, this seems to be the most cost-effective, efficient, and viable solution. The robot uses deep learning for image detection, and the object is acquired using robotic manipulators. The robot uses a Cartesian and articulated configuration to perform the picking action. In the end, the robot is operated where carrots and cantaloupes were harvested. The data of the harvested crops are used to arrive at the conclusion of the robot's accuracy.

show abstract

Section: Proposed Solutionmentioning

confidence: 99%

Agricultural harvesting using integrated robot system

Raja¹,

B²,

Nagaraj³

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…They compared Faster R-CNN with YOLOv3 and SSD and concluded that the YOLOv3 model is faster than both SSD and Faster R-CNN model and YOLOv3 has the best accuracy of 82% [42]. Moreover, several research efforts [61][62][63] conclude that a two-stage detector such as Faster R-CNN always has a better precision rate with a lower speed compared to a one stage-detector such as YOLOv5. Balancing the potholes detection accuracy and processing (inference) time is needed.…”

Section: Model-based Approaches For Potholes Detection Techniquesmentioning

confidence: 99%

Smart Pothole Detection Using Deep Learning Based on Dilated Convolution

Ahmed

2021

Sensors

View full text Add to dashboard Cite

Roads make a huge contribution to the economy and act as a platform for transportation. Potholes in roads are one of the major concerns in transportation infrastructure. A lot of research has proposed using computer vision techniques to automate pothole detection that include a wide range of image processing and object detection algorithms. There is a need to automate the pothole detection process with adequate accuracy and speed and implement the process easily and with low setup cost. In this paper, we have developed efficient deep learning convolution neural networks (CNNs) to detect potholes in real-time with adequate accuracy. To reduce the computational cost and improve the training results, this paper proposes a modified VGG16 (MVGG16) network by removing some convolution layers and using different dilation rates. Moreover, this paper uses the MVGG16 as a backbone network for the Faster R-CNN. In addition, this work compares the performance of YOLOv5 (Large (Yl), Medium (Ym), and Small (Ys)) models with ResNet101 backbone and Faster R-CNN with ResNet50(FPN), VGG16, MobileNetV2, InceptionV3, and MVGG16 backbones. The experimental results show that the Ys model is more applicable for real-time pothole detection because of its speed. In addition, using the MVGG16 network as the backbone of the Faster R-CNN provides better mean precision and shorter inference time than using VGG16, InceptionV3, or MobilNetV2 backbones. The proposed MVGG16 succeeds in balancing the pothole detection accuracy and speed.

show abstract

“…In this study, we will only be using a 125 pair image dataset trained by the Faster-RCNN method. The Faster R-CNN method proves to be good for training on a small dataset [20]. The machine learning model will be trained using phyton programing language and detectron2 framework in the identity document card detection process.…”

Section: Faster R-cnn Detectionmentioning

confidence: 99%

“…The machine learning model will be trained using phyton programing language and detectron2 framework in the identity document card detection process. Detectron2 [20] is a module from Facebook with the weight of pre-trained Faster R-CNN architecture with the same base model as the original paper proposed [9].…”

Section: Faster R-cnn Detectionmentioning

confidence: 99%

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

Hudaya

Saadah

Irawan

2021

RESTI

View full text Add to dashboard Cite

needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.

show abstract

Comparative analysis of deep learning image detection algorithms

Cited by 197 publications

References 37 publications

Agricultural harvesting using integrated robot system

Agricultural harvesting using integrated robot system

Smart Pothole Detection Using Deep Learning Based on Dilated Convolution

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

Contact Info

Product

Resources

About