Moving object detection under different weather conditions using full-spectrum light sources

Boukhriss, Rania Rebai; Fendri, Emna; Hammami, Mohamed

doi:10.1016/j.patrec.2019.11.004

Cited by 26 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Xavier initialization is performed to initialise the model. For anchors, the scale parameters are [10,3,2,4] and [16,3,2,4] for input resolutions of 321 × 321 and 513 × 513, respectively. The aspect ratios of the anchor are same as those of STDN.…”

Section: Experimental Settingmentioning

confidence: 99%

Robust object detection under harsh autonomous‐driving environments

Kim

Hwang

Shin

2021

IET Image Processing

View full text Add to dashboard Cite

In the autonomous driving environment, object instances in an image can be affected by various factors such as camera, driving state, weather, and system component. However, the deep learning-based vision systems are vulnerable to perturbation, which contains noise. Thus, robust object detection under harsh autonomous-driving environments is a more difficult than the generic situation. In this paper, it is found that not only the accuracy, but also the speed of the non-maximum suppression-based detector can be degraded under harsh environments. Therefore, object detection is handled under a harsh situation with adversarial mechanisms such as adversarial training and adversarial defence. Adversarial defence modules are designed to improve robustness in feature extraction level and define perturbations under a harsh environment for training object detectors to improve the robustness of the model's decision boundary. The proposed adversarial defence and training mechanisms improve the object detector in both accuracy and speed. The proposed method shows a 43.7% mean average precision for the COCO2015 dataset in generic object detection and 39.0% mean average precision for the BDD100K dataset in a driving environment. Furthermore, it achieves a real-time capability of 23 frames per second. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Experimental Settingmentioning

confidence: 99%

Robust object detection under harsh autonomous‐driving environments

Kim

Hwang

Shin

2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Deteksi objek dapat dilakukan dalam beberapa cara diantaranya dengan suara [1], [2], gambar [3], dan sensor [4]. Segmentasi merupakan salah satu proses yang digunakan untuk mendeteksi objek gambar.…”

Section: Pendahuluanunclassified

Segmentasi Citra Menggunakan Metode Watershed Transform Berdasarkan Image Enhancement Dalam Mendeteksi Embrio Telur

Saifullah

2020

SYSTEMIC

View full text Add to dashboard Cite

Image processing dapat diterapkan dalam proses deteksi embrio telur. Proses deteksi embrio telur dilakukan dengan menggunakan proses segmentasi, yang membagi citra sesuai dengan daerah yang dibagi. Proses ini memerlukan perbaikan citra yang diproses untuk memperoleh hasil optimal. Penelitian ini akan menganalisis deteksi embrio telur berdasarkan image processing dengan image enhancement dan konsep segmentasi menggunakan metode watershed transform. Image enhacement pada preprocessing dalam perbaikan citra menggunakan kombinasi metode Contrast Limited Adaptive Histogram Equalization (CLAHE) dan Histogram Equalization (HE). Citra grayscale telur diperbaiki dengan menggunakan metode CLAHE, dan hasilnya diproses kembali dengan menggunakan HE. Hasil perbaikan citra menunjukkan bahwa metode kombinasi CLAHE-HE memberikan gambar secara jelas daerah objek citra telur yang memiliki embrio. Proses segmentasi dengan menggunakan konversi citra ke citra hitam putih dan segmentasi watershed mampu menunjukkan secara jelas objek telur ayam yang memiliki embrio. Hasil segmentasi mampu membagi daerah telur memiliki embrio secara nyata dan akurat dengan persentase sebesar » 98%.

show abstract

“…CNN aims to reduce the complexity of the model and extract significant features by applying a convolution operation [17]. In visual data, object detection is a technique to find a candidate region for a detection target to recognize a specific target and to predict the type and location of the object (bounding box) [18,19]. The algorithms for this include R-CNN [20], Fast-R-CNN [21], Faster-R-CNN [22], and YOLO [23].…”

Section: Image Object Detection Algorithmmentioning

confidence: 99%

Pothole Classification Model Using Edge Detection in Road Image

Baek

Chung

2020

Applied Sciences

View full text Add to dashboard Cite

Since the image related to road damage includes objects such as potholes, cracks, shadows, and lanes, there is a problem that it is difficult to detect a specific object. In this paper, we propose a pothole classification model using edge detection in road image. The proposed method converts RGB (red green and blue) image data, including potholes and other objects, to gray-scale to reduce the amount of computation. It detects all objects except potholes using an object detection algorithm. The detected object is removed, and a pixel value of 255 is assigned to process it as a background. In addition, to extract the characteristics of a pothole, the contour of the pothole is extracted through edge detection. Finally, potholes are detected and classified based by the (you only look once) YOLO algorithm. The performance evaluation evaluates the distortion rate and restoration rate of the image, and the validity of the model and accuracy of the classification. The result of the evaluation shows that the mean square error (MSE) of the distortion rate and restoration rate of the proposed method has errors of 0.2–0.44. The peak signal to noise ratio (PSNR) is evaluated as 50 db or higher. The structural similarity index map (SSIM) is evaluated as 0.71–0.82. In addition, the result of the pothole classification shows that the area under curve (AUC) is evaluated as 0.9.

show abstract

Moving object detection under different weather conditions using full-spectrum light sources

Cited by 26 publications

References 20 publications

Robust object detection under harsh autonomous‐driving environments

Robust object detection under harsh autonomous‐driving environments

Segmentasi Citra Menggunakan Metode Watershed Transform Berdasarkan Image Enhancement Dalam Mendeteksi Embrio Telur

Pothole Classification Model Using Edge Detection in Road Image

Contact Info

Product

Resources

About