A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3

Zhang, Xiang; Yang, Wei; Tang, Xiaolin; Liu, Jie

doi:10.3390/s18124308

Cited by 70 publications

(48 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the authors' knowledge, there is no software to automatically generate labeled datasets of rats in the PASCAL VOC format. In the current study, the marked datasets of Sprague Dawley (SD) rats are rare and not opensource, and Zhang proposed a method for the automatic generation of the lane label images [21]. Thus, a method to automatically generate marked datasets for SD rats in a fixed simple scene was proposed and in order to avoid some mistakes in the automatic system and increase the accuracy of marking, the generated datasets can be manually modified using the LabelImg software.…”

Section: Automatic Generating Labeled Datasetmentioning

confidence: 99%

“…However, Joseph Redmon proposed a YOLO v3 framework [17] in 2018 which is better than YOLO v2 [18] at small object detection, faster than Mask-RCNN, and has higher detection accuracy than DSSD (Deconvolutional Single Shot Detector) [19]. The deep learning framework has been used in some studies in different fields, for example, Koirala [20] used the framework to estimate the yield of mango, Zhang [21] used the framework to detect the lane in real time, and Tian [22] used the framework to detect apples in real time during different growth stages. In this study, we apply the YOLO v3 in our project as the state-of-art detection and localization algorithm for rats.As it is inevitable that it is impossible to detect objects in every frame, for the position prediction in the next frame, it is necessary to fill the object in the image.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Robust Real-Time Detecting and Tracking Framework for Multiple Kinds of Unmarked Object

Dai

Chen

et al. 2019

Sensors

View full text Add to dashboard Cite

A rodent real-time tracking framework is proposed to automatically detect and track multi-objects in real time and output the coordinates of each object, which combines deep learning (YOLO v3: You Only Look Once, v3), the Kalman Filter, improved Hungarian algorithm, and the nine-point position correction algorithm. A model of a Rat-YOLO is trained in our experiment. The Kalman Filter model is established in an acceleration model to predict the position of the rat in the next frame. The predicted data is used to fill the losing position of rats if the Rat-YOLO doesn't work in the current frame, and to associate the ID between the last frame and current frame. The Hungarian assigned algorithm is used to show the relationship between the objects of the last frame and the objects of the current frame and match the ID of the objects. The nine-point position correction algorithm is presented to adjust the correctness of the Rat-YOLO result and the predicted results. As the training of deep learning needs more datasets than our experiment, and it is time-consuming to process manual marking, automatic software for generating labeled datasets is proposed under a fixed scene and the labeled datasets are manually verified in term of their correctness. Besides this, in an off-line experiment, a mask is presented to remove the highlight. In this experiment, we select the 500 frames of the data as the training datasets and label these images with the automatic label generating software. A video (of 2892 frames) is tested by the trained Rat model and the accuracy of detecting all the three rats is around 72.545%, however, the Rat-YOLO combining the Kalman Filter and nine-point position correction arithmetic improved the accuracy to 95.194%.Sensors 2020, 20, 2 2 of 17 to children with autism [4]. As the social behavior is more complex than we can image, some works focus on the interaction between two rats [5,6], and real-time target tracking throughout the process provides a more comprehensive analysis of animal neural activity in studying animal neural activity. In the past survey of social behavior, the focus of research has been the interaction between the two rats in a cage [7,8]. Therefore, the research of social behavior with more than two rats is a good research direction to study SI in the future.The development of machine vision has been ongoing rapidly along with the development of deep learning in recent years. The current detection method of rats is based on the traditional image processing methods, such as background subtraction [9,10], but by this method, the background is generally set as simple, and there is a great contrast between the detected object and background in the histogram of the image. However, some social behavior requires experiments to be in different scenes, and the experimental background is dynamic rather than static; thus, the method make it more possible to recognize fault objects in the condition, Furthermore, using more complex arithmetic solves this problem which may consume more time. In c...

show abstract

Section: Automatic Generating Labeled Datasetmentioning

confidence: 99%

mentioning

confidence: 99%

A Robust Real-Time Detecting and Tracking Framework for Multiple Kinds of Unmarked Object

Dai

Chen

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…With the aid of deep learning, outstanding deep neural networks (DNNs) models are proposed so as to generate high precision, approximately 85%, human body profiles in PMMW images [6]. Additionally, YOLOv3 algorithms have been successfully applied for real-time detection of targets such as cars, rail surface defects, and airplanes and other things [27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Real-time Concealed Object Detection from Passive Millimeter Wave Images Based on the YOLOv3 Algorithm

Pang

Liu

Chen

et al. 2020

Sensors

View full text Add to dashboard Cite

The detection of objects concealed under people’s clothing is a very challenging task, which has crucial applications for security. When testing the human body for metal contraband, the concealed targets are usually small in size and are required to be detected within a few seconds. Focusing on weapon detection, this paper proposes using a real-time detection method for detecting concealed metallic weapons on the human body applied to passive millimeter wave (PMMW) imagery based on the You Only Look Once (YOLO) algorithm, YOLOv3, and a small sample dataset. The experimental results from YOLOv3-13, YOLOv3-53, and Single Shot MultiBox Detector (SSD) algorithm, SSD-VGG16, are compared ultimately, using the same PMMW dataset. For the perspective of detection accuracy, detection speed, and computation resource, it shows that the YOLOv3-53 model had a detection speed of 36 frames per second (FPS) and a mean average precision (mAP) of 95% on a GPU-1080Ti computer, more effective and feasible for the real-time detection of weapon contraband on human body for PMMW images, even with small sample data.

show abstract

“…As well as being able to validate results, key strengths of this approach, compared to existing options, include it being consistent, comparatively fast, standardised, and relatively free from biases associated with anthropomorphic values and operator fatigue. Advances in computer vision have been pronounced of recent years with successful demonstrations of image recognition in fields as diverse as autonomous cars, citrus tree detection from drone imagery and identification of skin cancer (Zhang et al 2018;Csillik et al 2018;Esteva et al 2017). Recent work has also demonstrated the feasibility of Deep Learning approaches for species identification in camera trap images although it is worth noting that such algorithms have been used in prototype software for this purpose since at least 2015 in projects such as Wild Dog Alert (https://invasives.com.au/research/wild-dog-alert/ ) (Meek et al in press) building on earlier semi-automated species recognition algorithms (Falzon, Meek & Vernes 2014).…”

Section: Introductionmentioning

confidence: 99%

ClassifyMe: a field-scouting software for the identification of wildlife in camera trap images

Falzon¹,

Lawson²,

Cheung³

et al. 2019

Preprint

View full text Add to dashboard Cite

We present ClassifyMe a software tool for the automated identification of animal species from camera trap images. ClassifyMe is intended to be used by ecologists both in the field and in the office. Users can download a pre-trained model specific to their location of interest and then upload the images from a camera trap to a laptop or workstation. ClassifyMe will identify animals and other objects (e.g. vehicles) in images, provide a report file with the most likely species detections and automatically sort the images into sub-folders corresponding to these species categories. False Triggers (no visible object present) will also be filtered and sorted. Importantly, the ClassifyMe software operates on the user's local machine (own laptop or workstation) not via internet connection. This allows users access to state-of-the-art camera trap computer vision software in situ, rather than only in the office. The software also incurs minimal cost on the end-user as there is no need for expensive data uploads to cloud services. Furthermore, processing the images locally on the users' end-device allows them data control and resolves privacy issues surrounding transfer and third-party access to users' datasets.

show abstract

A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3

Cited by 70 publications

References 40 publications

A Robust Real-Time Detecting and Tracking Framework for Multiple Kinds of Unmarked Object

A Robust Real-Time Detecting and Tracking Framework for Multiple Kinds of Unmarked Object

Real-time Concealed Object Detection from Passive Millimeter Wave Images Based on the YOLOv3 Algorithm

ClassifyMe: a field-scouting software for the identification of wildlife in camera trap images

Contact Info

Product

Resources

About