Semantic Segmentation Based Traffic Light Detection at Day and at Night

Haltakov, Vladimir; Mayr, Jakob; Unger, Christian; Ilić, Slobodan

doi:10.1007/978-3-319-24947-6_37

Cited by 34 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wang and Ren [3] improved the image contrast by preprocessing with median filtering and the histogram equalization method, and segmented a single object using the brightness and color difference between the background and foreground pixels. Haltakov et al [4] used texture and color information to segment the candidate regions of a single object. Alpar [5] obtained the differential image after subtracting the greyscale image from the red channel image.…”

Section: Related Workmentioning

confidence: 99%

“…From epoch 1 to epoch 200, the learning rate remains the same at 0.0004, and for the remaining 100 epochs, It was set so that the learning rate decreases linearly to 0. To balance between the respective loss values, the λof equation (4) was set at 10. The input image size of our network was resized to 320 × 240 pixels (width and height, respectively) for the CamVid AND Syn-CamVid databases, and 512 × 176 pixels (width and height, respectively) for the KITTI and Syn-KITTI databases, considering the aspect ratio of the two databases used in the experiment.…”

Section: B Training Of Modified Cycleganmentioning

confidence: 99%

See 1 more Smart Citation

Semantic Segmentation With Low Light Images by Modified CycleGAN-Based Image Enhancement

et al. 2020

View full text Add to dashboard Cite

In recent years, the importance of semantic segmentation has been widely recognized and the field has been actively studied. The existing state-of-the-art segmentation methods show high performance for bright and clear images. However, in low light or nighttime environments, images are blurred and noise increases due to the nature of the camera sensor, which makes it very difficult to perform segmentation for various objects. For this reason, there are few previous studies on multi-class segmentation in low light or nighttime environments. To address this challenge, we propose a modified cycle generative adversarial network (CycleGAN)-based multi-class segmentation method that improves multi-class segmentation performance for low light images. In this study, we used low light databases generated by two road scene open databases that provide segmentation labels, which are the Cambridge-driving labeled video database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) database. Consequently, the proposed method showed superior segmentation performance compared with the other state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: B Training Of Modified Cycleganmentioning

confidence: 99%

Semantic Segmentation With Low Light Images by Modified CycleGAN-Based Image Enhancement

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Accordingly, various methods for object segmentation have been studied in low light or nighttime environments [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. In handcrafted feature-based segmentation studies [1][2][3][4][5][6][7][8][9], segmentation is performed by classifying the single object region as foreground and the rest of the areas as background in a low light environment. In this case, unique handcrafted features of a single target object (foreground) are used to distinguish the background region from the foreground region, thus resulting in a relatively better and more accurate segmentation performance.…”

Section: Introductionmentioning

confidence: 99%

Modified Perceptual Cycle Generative Adversarial Network-Based Image Enhancement for Improving Accuracy of Low Light Image Segmentation

et al. 2021

View full text Add to dashboard Cite

In recent years, the importance of the semantic segmentation field has been increasingly emphasized because autonomous vehicle and artificial intelligence (AI)-based robot technology are being researched extensively; and methods for accurately recognizing objects are required. Previous state-of-theart segmentation methods have been proven to be effective for databases obtained during daytime. However, in extremely low light or nighttime environments, the shape and color information of objects are very small or disappear due to an insufficient amount of external light, which makes it difficult to train the segmentation network and significantly degrades performance. In our previous work, segmentation performance in a low light environment was improved using the enhancement-based segmentation method. However, low light images could not be restored precisely and segmentation performance improvement was limited because only per-pixel loss functions were used when training the enhancement network. To overcome these drawbacks, we propose a low light image segmentation method based on a modified perceptual cycle generative adversarial network (CycleGAN). Perceptual image enhancement was performed using our network, which significantly improved segmentation performance. Unlike the existing perceptual loss, the Euclidean distance of the feature maps extracted from the pretrained segmentation network was used.In our experiments, we used low light databases generated from two famous road scene open databases, which are Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI), and confirmed that our proposed method shows better segmentation performance in extremely low light environments than the existing state-of-the art methods. INDEX TERMSSemantic segmentation; Low light; Modified perceptual CycleGAN; Perceptual loss; Road scene open database.

show abstract

“…Bu sayede gerçekçi koşullar altında imgeler üzerindeki bozucu etkilerin dinamik olarak değiştiği ve tespit edilemediği durumları barındıran görsel bir veri seti kullanılmıştır. Bu veri seti literatürde çok sayıda çalışmada kullanılmaktadır [7][8][9][10][11][12]. Spot ışığı bulma ve uyarlanabilir trafik ışığı şablonuna dayanan bir trafik ışığı tanıma sistemi [7,8] çalışmalarında sunulmuştur.…”

Section: Gi̇ri̇ş (Introduction)unclassified

“…Wang ve arkadaşları [10], morfolojik işlemler ve şekilsel özelliklerle imgeleri filtrelemiş ve şablon eşlemeye dayalı bir yöntem önermişlerdir. [11] [13]. Eşik bulma işlemi için imgenin histogramının ortalaması, olasılıkları ve varyansları kullanılmıştır.…”

Section: Gi̇ri̇ş (Introduction)unclassified

Trafik Işığı Tespiti Yapan Bir Sürücü Güvenlik Destek Sistemi

Kılıkçıer¹,

Yilmaz²

2018

Journal of Polytechnic

View full text Add to dashboard Cite

Semantic Segmentation Based Traffic Light Detection at Day and at Night

Cited by 34 publications

References 18 publications

Semantic Segmentation With Low Light Images by Modified CycleGAN-Based Image Enhancement

Semantic Segmentation With Low Light Images by Modified CycleGAN-Based Image Enhancement

Modified Perceptual Cycle Generative Adversarial Network-Based Image Enhancement for Improving Accuracy of Low Light Image Segmentation

Trafik Işığı Tespiti Yapan Bir Sürücü Güvenlik Destek Sistemi

Contact Info

Product

Resources

About