Deep neural network based date palm tree detection in drone imagery

Jintasuttisak, Thani; Edirisinghe, Eran A.; El-Battay, A.

doi:10.1016/j.compag.2021.106560

Cited by 84 publications

(57 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shi et al ( 2020 ) designs channel and spatial masks based on the YOLOv3-tiny network to detect convolution kernels in the network that are closely related to specific target outputs, resulting in more efficient mango detection. Jintasuttisak et al ( 2022 ) used the YOLOv5-m network to detect crowded date palms in UAV images. A series of networks from RCNN (Girshick et al, 2014 ) to Faster RCNN (Ren et al, 2017 ) are typical two-stage methods in object detection.…”

Section: Related Workmentioning

confidence: 99%

Cotton boll localization method based on point annotation and multi-scale fusion

Sun

Yang

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Cotton is an important source of fiber. The precise and intelligent management of cotton fields is the top priority of cotton production. Many intelligent management methods of cotton fields are inseparable from cotton boll localization, such as automated cotton picking, sustainable boll pest control, boll maturity analysis, and yield estimation. At present, object detection methods are widely used for crop localization. However, object detection methods require relatively expensive bounding box annotations for supervised learning, and some non-object regions are inevitably included in the annotated bounding boxes. The features of these non-object regions may cause misjudgment by the network model. Unlike bounding box annotations, point annotations are less expensive to label and the annotated points are only likely to belong to the object. Considering these advantages of point annotation, a point annotation-based multi-scale cotton boll localization method is proposed, called MCBLNet. It is mainly composed of scene encoding for feature extraction, location decoding for localization prediction and localization map fusion for multi-scale information association. To evaluate the robustness and accuracy of MCBLNet, we conduct experiments on our constructed cotton boll localization (CBL) dataset (300 in-field cotton boll images). Experimental results demonstrate that MCBLNet method improves by 49.4% average precision on CBL dataset compared with typically point-based localization state-of-the-arts. Additionally, MCBLNet method outperforms or at least comparable with common object detection methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Cotton boll localization method based on point annotation and multi-scale fusion

Sun

Yang

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…The YOLOv5x model also has the best loss value. In the study of palm tree detection, although all YOLO models have similar training time, YOLOv5s model is minimum [26] (p. 8). In our case, there is a larger gap between the minimum (48 minutes) and maximum (379 minutes) training time.…”

Section: Discussionmentioning

confidence: 99%

YOLOv3, YOLOv4 ve YOLOv5 algoritmalarının Performans Karşılaştırması: Kümes Hayvan Tanıma İçin Bir Vaka Çalışması

Kivrak

Gürbüz

2022

EJOSAT

View full text Add to dashboard Cite

Bu çalışmanın amacı, görüntüleri sınıflandırmak için kullanılan popüler evrişim sinir ağı modellerinin arasındaki performans farklılıklarını bulmaktır. Bunun için, YOLO modelinin farklı versiyonları üzerinde bir vaka çalışması yürütüldü. Bu çalışma için yeni bir veri seti oluşturulmuştur. Oluşturulan veri setinde, 918 adet tavuk, horoz ve civciv görüntülerini içeren kümes hayvanı fotoğrafları bulunmaktadır. Veri kümesinin % 80'i eğitim % 20 test olarak ayrılmıştır. Eğitim ve test veri kümelerindeki kümes hayvanlarının görüntüleri manuel olarak etiketlendi. Eğitim veri kümelesindeki görüntüler YOLOv3-tiny, YOLOv3, YOLOv4-tiny, YOLOv4, YOLOv5s, ve YOLOv5x modelleri kullanılarak eğitim tamamlandı. Kümes hayvanı tespiti için YOLOv5' modeli ile elde edilen sonuçlar diğer popüler CNN mimarisi sahip olan YOLOv3 YOLOv4 modelleri ile karşılaştırılmıştır. Sonuç olarak YOLOv5x(XLarge Depth(derinlik)) modeli 0,5 IOU'da %99,5 ortalama hassasiyetle en yüksek doğruluk oranı bulunmuştur.

show abstract

“…They claimed to have achieved an accuracy of 95% for classifying the digits. There are other researchers [ 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 ] who have proposed different approaches for the detection of license plates of vehicles. Table 1 provides a summary of this research.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

Batra

Hussain

Ahad

et al. 2022

Sensors

View full text Add to dashboard Cite

With the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulation, etc. At present, most of these systems rely heavily on high-end computing resources. This paper proposes a novel memory and time-efficient automatic license plate recognition (ALPR) system developed using YOLOv5. This approach is ideal for IoT devices that usually have less memory and processing power. Our approach incorporates two stages, i.e., using a custom transfer learned model for license plate detection and an LSTM-based OCR engine for recognition. The dataset that we used for this research was our dataset consisting of images from the Google open images dataset and the Indian License plate dataset. Along with training YOLOv5 models, we also trained YOLOv4 models on the same dataset to illustrate the size and performance-wise comparison. Our proposed ALPR system results in a 14 megabytes model with a mean average precision of 87.2% and 4.8 ms testing time on still images using Nvidia T4 GPU. The complete system with detection and recognition on the other hand takes about 85 milliseconds.

show abstract

Deep neural network based date palm tree detection in drone imagery

Cited by 84 publications

References 14 publications

Cotton boll localization method based on point annotation and multi-scale fusion

Cotton boll localization method based on point annotation and multi-scale fusion

YOLOv3, YOLOv4 ve YOLOv5 algoritmalarının Performans Karşılaştırması: Kümes Hayvan Tanıma İçin Bir Vaka Çalışması

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

Contact Info

Product

Resources

About