A Target Detection Model Based on Improved Tiny-Yolov3 Under the Environment of Mining Truck

Xiao, Dong; Shan, Feng; Li, Ze; Le, Ba Tuan; Liu, Xiwen; Li, Xuerao

doi:10.1109/access.2019.2928603

Cited by 48 publications

(23 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thai traffic signs were detected and recognized using CNNs with 93% average precision [21]. The Tiny-YOLOv3 was designed by simplifying the YOLOv3 algorithm and reducing the depth of convolutional layers, which significantly improved the inference speed and is also ideal for running on personal computers [22].…”

Section: Introductionmentioning

confidence: 99%

Design and Development of a Smart Variable Rate Sprayer Using Deep Learning

et al. 2020

View full text Add to dashboard Cite

The uniform application (UA) of agrochemicals results in the over-application of harmful chemicals, increases crop input costs, and deteriorates the environment when compared with variable rate application (VA). A smart variable rate sprayer (SVRS) was designed, developed, and tested using deep learning (DL) for VA application of agrochemicals. Real-time testing of the SVRS took place for detecting and spraying and/or skipping lambsquarters weed and early blight infected and healthy potato plants. About 24,000 images were collected from potato fields in Prince Edward Island and New Brunswick under varying sunny, cloudy, and partly cloudy conditions and processed/trained using YOLOv3 and tiny-YOLOv3 models. Due to faster performance, the tiny-YOLOv3 was chosen to deploy in SVRS. A laboratory experiment was designed under factorial arrangements, where the two spraying techniques (UA and VA) and the three weather conditions (cloudy, partly cloudy, and sunny) were the two independent variables with spray volume consumption as a response variable. The experimental treatments had six repetitions in a 2 × 3 factorial design. Results of the two-way ANOVA showed a significant effect of spraying application techniques on volume consumption of spraying liquid (p-value < 0.05). There was no significant effect of weather conditions and interactions between the two independent variables on volume consumption during weeds and simulated diseased plant detection experiments (p-value > 0.05). The SVRS was able to save 42 and 43% spraying liquid during weeds and simulated diseased plant detection experiments, respectively. Water sensitive papers’ analysis showed the applicability of SVRS for VA with >40% savings of spraying liquid by SVRS when compared with UA. Field applications of this technique would reduce the crop input costs and the environmental risks in conditions (weed and disease) like experimental testing.

show abstract

Section: Introductionmentioning

confidence: 99%

Design and Development of a Smart Variable Rate Sprayer Using Deep Learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The surge loader [3] can also operate autonomously. For autonomous vehicles to operate successfully they need to be aware of the distance between themselves and other vehicles with enough time to make safe and reliable mission plans [32,33]. The use of cameras and sensors are therefore not only essential for the correct operation of these vehicles and equipment but to also maintain the high standards of safety necessary in the mining industry [18,20].…”

Section: Sensors and Cameras Systemmentioning

confidence: 99%

“…In addition to reducing truck loading time, this reduces the overall truck cycle time. The proximity detection system of the surge loader reduces operational maneuvers of trucks (turns, reversing, stopping, or exiting the route), due to the ability to detect and eliminate blind spots [32,35]. The decrease in the probability of collisions during normal driving, parking, or maintenance maneuvers is another benefit associated with the detection system.…”

Section: Travel Routesmentioning

confidence: 99%

Optimising Productivity and Safety of the Open Pit Loading and Haulage System with a Surge Loader

Aguayo

Nehring

Ullah

2021

Mining

View full text Add to dashboard Cite

The open pit mining load and haul system has been a mainstay of the mining industry for many years. While machines have increased in size and scale and automation has become an important development, there have been few innovations to the actual load and haul process itself in recent times. This research highlights some of the potential productivity and safety benefits that the incorporation of a surge loader may bring to the load and haul system through an analysis of the system, discussion of component characteristics, and mine planning aspects. The incorporation of the surge loader into open pit loading and haulage operations also enables improved safety. This is a result of a reduction in shovel–truck interactions and the reduced likelihood of truck overfilling and uneven loading. This paper details the number of mine worker deaths that a surge loader may have prevented within the Peruvian and Chilean mining industries.

show abstract

“…The main metric for accuracy on these models have been mean average precision (mAP) [4]. Tiny YOLOv3 was developed as a simplified version of YOLOv3, it uses seven layers (instead of Darknet-53) and the features are identified by small layers of 1X1 and 3X3, but at the end the loss function is the same as YOLOv3 [5].…”

Section: Related Workmentioning

confidence: 99%

“…where T h is the total number of features found by HOG descriptor, B i are the blocks of the image, In the reviewed literature for measuring accuracy or performance it has been a constant to use Average Precision (AP) [9] and mean Average Precision (mAP) [3][4][5]10]. AP finds the area under the precision recall curve from 0 to 1 expressed as:…”

Section: Related Workmentioning

confidence: 99%

Vision Acuity Index. A Novel Metric to Select the Best Fit Computer Vision Algorithm for Smart Cities and Industry 4.0

Contreras-Masse¹,

Ochoa²,

Argüelles³

et al. 2020

Preprint

View full text Add to dashboard Cite

Computer vision is considered as an ally to solve business problems that require human intervention, intelligence and criteria. This topic of research has evolved in XXI century at faster peace, delivering various alternatives from open source until commercial platforms. With so many options and market growing, it result difficult to make a decision on which one to use, or even worse, realize it was not suited for different scenarios. In this paper we analyze five options selected arbitrarily and tested on a dataset of 755 images to detect persons in an image, using object detectors. We analyze elapsed time to process an image, error with observations by humans, number of persons detected, correlation of time and person density, object detected size and F1 Score, considering precision and recall. As we found there are score ties and similar behaviors among options available, we introduce a novel index that takes in consideration the number of persons and their pixel size, to propose the Vision Acuity Index of Computer Vision. The results demonstrate this is a good option to serve as indicator to make decisions. Also, this index proposed have a potential to be expanded for different business use cases, and to measure new proposed algorithms in the future along with the traditional metrics used previously.

show abstract

A Target Detection Model Based on Improved Tiny-Yolov3 Under the Environment of Mining Truck

Cited by 48 publications

References 6 publications

Design and Development of a Smart Variable Rate Sprayer Using Deep Learning

Design and Development of a Smart Variable Rate Sprayer Using Deep Learning

Optimising Productivity and Safety of the Open Pit Loading and Haulage System with a Surge Loader

Vision Acuity Index. A Novel Metric to Select the Best Fit Computer Vision Algorithm for Smart Cities and Industry 4.0

Contact Info

Product

Resources

About