Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
18 results
Search Results
Now showing 1 - 10 of 18
Conference Object Citation - WoS: 7Citation - Scopus: 6Semantic Pose Verification for Outdoor Visual Localization With Self-Supervised Contrastive Learning(IEEE, 2022) Guerrero, Jose J.; Orhan, Semih; Baştanlar, YalınAny city-scale visual localization system has to overcome long-term appearance changes, such as varying illumination conditions or seasonal changes between query and database images. Since semantic content is more robust to such changes, we exploit semantic information to improve visual localization. In our scenario, the database consists of gnomonic views generated from panoramic images (e.g. Google Street View) and query images are collected with a standard field-of-view camera at a different time. To improve localization, we check the semantic similarity between query and database images, which is not trivial since the position and viewpoint of the cameras do not exactly match. To learn similarity, we propose training a CNN in a self-supervised fashion with contrastive learning on a dataset of semantically segmented images. With experiments we showed that this semantic similarity estimation approach works better than measuring the similarity at pixel-level. Finally, we used the semantic similarity scores to verify the retrievals obtained by a state-of-the-art visual localization method and observed that contrastive learning-based pose verification increases top-1 recall value to 0.90 which corresponds to a 2% improvement.Article Citation - WoS: 7Citation - Scopus: 8Long-Term Image-Based Vehicle Localization Improved With Learnt Semantic Descriptors(Elsevier, 2022) Çınaroğlu, İbrahim; Baştanlar, YalınVision based solutions for the localization of vehicles have become popular recently. In this study, we employ an image retrieval based visual localization approach, in which database images are kept with GPS coordinates and the location of the retrieved database image serves as the position estimate of the query image in a city scale driving scenario. Regarding this approach, most existing studies only use descriptors extracted from RGB images and do not exploit semantic content. We show that localization can be improved via descriptors extracted from semantically segmented images, especially when the environment is subjected to severe illumination, seasonal or other long-term changes. We worked on two separate visual localization datasets, one of which (Malaga Streetview Challenge) has been generated by us and made publicly available. Following the extraction of semantic labels in images, we trained a CNN model for localization in a weakly-supervised fashion with triplet ranking loss. The optimized semantic descriptor can be used on its own for localization or preferably it can be used together with a state-of-the-art RGB image based descriptor in hybrid fashion to improve accuracy. Our experiments reveal that the proposed hybrid method is able to increase the localization performance of the standard (RGB image based) approach up to 7.7% regarding Top-1 Recall values.Article Citation - WoS: 3Citation - Scopus: 3Catadioptric Hyperspectral Imaging, an Unmixing Approach(Institution of Engineering and Technology, 2020) Özışık Başkurt, Didem; Baştanlar, Yalın; Yardımcı Çetin, YaseminHyperspectral imaging systems provide dense spectral information on the scene under investigation by collecting data from a high number of contiguous bands of the electromagnetic spectrum. The low spatial resolutions of these sensors frequently give rise to the mixing problem in remote sensing applications. Several unmixing approaches are developed in order to handle the challenging mixing problem on perspective images. On the other hand, omnidirectional imaging systems provide a 360-degree field of view in a single image at the expense of lower spatial resolution. In this study, we propose a novel imaging system which integrates hyperspectral cameras with mirrors so on to yield catadioptric omnidirectional imaging systems to benefit from the advantages of both modes. Catadioptric images, incorporating a camera with a reflecting device, introduce radial warping depending on the structure of the mirror used in the system. This warping causes a non-uniformity in the spatial resolution which further complicates the unmixing problem. In this context, a novel spatial-contextual unmixing algorithm specifically for the large field of view of the hyperspectral imaging system is developed. The proposed algorithm is evaluated on various real-world and simulated cases. The experimental results show that the proposed approach outperforms compared methods.Conference Object Zamanda ortalaması alınmış ikili önplan imgeleri kullanarak taşıt sınıflandırması(IEEE, 2015) Karaimer, Hakkı Can; Baştanlar, YalınWe describe a shape-based method for classification of vehicles from omnidirectional videos. Different from similar approaches, the binary images of vehicles obtained by background subtraction in a sequence of frames are averaged over time. We show with experiments that using the average shape of the object results in a more accurate classification than using a single frame. The vehicle types we classify are motorcycle, car and van. We created an omnidirectional video dataset and repeated experiments with shuffled train-test sets to ensure randomization.Article Citation - WoS: 3Citation - Scopus: 3Elimination of Useless Images From Raw Camera-Trap Data(Türkiye Klinikleri Journal of Medical Sciences, 2019) Tekeli, Ulaş; Baştanlar, YalınCamera-traps are motion triggered cameras that are used to observe animals in nature. The number of images collected from camera-traps has increased significantly with the widening use of camera-traps thanks to advances in digital technology. A great workload is required for wild-life researchers to group and label these images. We propose a system to decrease the amount of time spent by the researchers by eliminating useless images from raw camera-trap data. These images are too bright, too dark, blurred, or they contain no animals To eliminate bright, dark, and blurred images we employ techniques based on image histograms and fast Fourier transform. To eliminate the images without animals, we propose a system combining convolutional neural networks and background subtraction. We experimentally show that the proposed approach keeps 99% of photos with animals while eliminating more than 50% of photos without animals. We also present a software prototype that employs developed algorithms to eliminate useless images.Conference Object Citation - WoS: 2Citation - Scopus: 8İnsansız Araçlar için Anlamsal Bölütleme ile İmge Tabanlı Konumlandırma(Institute of Electrical and Electronics Engineers Inc., 2019) Çınaroğlu, İbrahim; Baştanlar, YalınBilgisayarlı Görü alanındaki popülerliğini koruyan araştırma konularından birisi insansız araçlarda yer tespiti ve konumlandırmadır. Araçların konumlandırılmasında kullanılan GPS sistemlerinin bazı durumlarda faal olamadığı bilinen bir gerçektir ve bu yetersizlik imge tabanlı konumlandırma çalışmalarına hız vermiştir. Bizim çalışmamızda, araç içinden elde edilmiş Malaga şehir merkezi görüntülerinden oluşan bir veri tabanı kullanılarak imge tabanlı konumlandırma yapılmıştır. İlk olarak, anlamsal (semantik) bölütleme sonucunda elde edilen bir anlamsal betimleyici oluşturulmuş ve yaklaşık en yakın komşuluk araması tekniği de kullanılarak bir konumlandırma yapılmıştır. Ardından bu yöntemin başarısı, literatürde sıkça kullanılan yerel betimleyici tabanlı yöntemin başarısıyla kıyaslanmıştır. Ayrıca, bu iki yöntemin birleştirilmesi ile elde edilen melez bir yöntem önerilmiştir. Önerilen melez imge-tabanlı konumlandırmanın, sadece yerel betimleyici ve sadece anlamsal betimleyici kullanan yöntemden daha başarılı olduğu, dolayısıyla yerel betimleyici tabanlı yöntemlerin anlamsal betimleyiciler ile desteklenmesinin başarıyı artırdığı, deneysel sonuçlarla gösterilmiştir.Article Citation - WoS: 9Citation - Scopus: 13Training Cnns With Image Patches for Object Localisation(Institution of Engineering and Technology, 2018) Orhan, Semih; Baştanlar, YalınRecently, convolutional neural networks (CNNs) have shown great performance in different problems of computer vision including object detection and localisation. A novel training approach is proposed for CNNs to localise some animal species whose bodies have distinctive patterns such as leopards and zebras. To learn characteristic patterns, small patches which are taken from different body parts of animals are used to train models. To find object location, in a test image, all locations are visited in a sliding window fashion. Crops are fed into trained CNN and their classification scores are combined into a heat map. Later on, heat maps are converted to bounding box estimates for varying confidence scores. The localisation performance of the patch-based training approach is compared with Faster R-CNN – a state-of-the-art CNN-based object detection and localisation method. Experimental results reveal that the patch-based training outperforms Faster R-CNN, especially for classes with distinctive patterns.Conference Object Citation - WoS: 4Citation - Scopus: 13Classification and Tracking of Traffic Scene Objects With Hybrid Camera Systems(Institute of Electrical and Electronics Engineers Inc., 2018) Barış, İpek; Baştanlar, YalınIn a hybrid camera system combining an omnidirectional and a Pan-Tilt-Zoom (PTZ) camera, the omnidirectional camera provides 360 degree horizontal field-of-view, whereas the PTZ camera provides high resolution at a certain direction. This results in a wide field-of-view and high resolution camera system. In this paper, we exploit this hybrid system for real-time object classification and tracking for traffic scenes. The omnidirectional camera detects the moving objects and performs an initial classification using shape-based features. Concurrently, the PTZ camera classifies the objects using high resolution frames and Histogram of Oriented Gradients (HOG) features. PTZ camera also performs high-resolution tracking for the objects classified as the target class by the omnidirectional camera. The object types we worked on are pedestrian, motorcycle, car and van. Extensive experiments were conducted to compare the classification accuracy of the hybrid system with single camera alternatives.Article Citation - WoS: 16Citation - Scopus: 16Detection and Classification of Vehicles From Omnidirectional Videos Using Multiple Silhouettes(Springer Verlag, 2017) Karaimer, Hakkı Can; Barış, İpek; Baştanlar, YalınTo detect and classify vehicles in omnidirectional videos, we propose an approach based on the shape (silhouette) of the moving object obtained by background subtraction. Different from other shape-based classification techniques, we exploit the information available in multiple frames of the video. We investigated two different approaches for this purpose. One is combining silhouettes extracted from a sequence of frames to create an average silhouette, the other is making individual decisions for all frames and use consensus of these decisions. Using multiple frames eliminates most of the wrong decisions which are caused by a poorly extracted silhouette from a single video frame. The vehicle types we classify are motorcycle, car (sedan) and van (minibus). The features extracted from the silhouettes are convexity, elongation, rectangularity and Hu moments. We applied two separate methods of classification. First one is a flowchart-based method that we developed and the second is K-nearest neighbour classification. 60% of the samples in the dataset are used for training. To ensure randomization in the experiments, threefold cross-validation is applied. The results indicate that using multiple silhouettes increases the classification performance.Conference Object Tümyönlü ve Ptz Kameralar ile Taşıt Sınıflandırması(Institute of Electrical and Electronics Engineers Inc., 2016) Barış, İpek; Baştanlar, YalınÇalışmamızda trafik sahneleri üzerindeki araçların tespit edilip sınıflandırması için bir tümyönlü bir de PTZ (pantilt-zoom) kamera kullanan bir yöntem önerilmiştir. Önerilen yöntem, tümyönlü kamerada arkaplan çıkarımı sonrası saptanan nesnenin konumuna göre PTZ kamerayı uygun açıya yönlendirmekte ve PTZ kamerada yapılan ikincil tespit sonrası çıkarılan öznitelikler ile araç sınıflandırılmaktadır. Sınıflandırma başarısı ayrıca sadece tümyönlü kamerada yapılan sınıflandırma ile karşılaştırılmıştır. Üzerine çalışılan nesne tipleri motorsiklet, araba, dolmuş ve yayadır.