京都大学 / 新制・課程博士 / 博士(工学) / 甲第24569号 / 工博第5075号 / 新制||工||1972(附属図書館) / 京都大学大学院工学研究科都市社会工学専攻 / (主査)教授 須崎 純一, 教授 宇野 伸宏, 准教授 松島 格也 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

No description available.

<p dir="ltr">Artificial Intelligence (AI) has revolutionized and accelerated significant advancements in various fields such as healthcare, finance, education, agriculture and the development of autonomous vehicles. We are rapidly approaching Level 5 Autonomy due to recent developments in autonomous technology, including self-driving cars, robot navigation, smart traffic monitoring systems, and dynamic routing. This success has been made possible due to Deep Learning technologies and advanced Computer Vision (CV) algorithms. With the help of perception sensors such as Camera, LiDAR and RADAR, CV algorithms enable a self-driving vehicle to interact with the environment and make intelligent decisions. Object detection lays the foundations for various applications, such as collision and obstacle avoidance, lane detection, pedestrian and vehicular safety, and object tracking. Object detection has two significant components: image classification and object localization. In recent years, enhancing the performance of 2D and 3D object detectors has spiked interest in the research community. This research aims to resolve the drawbacks associated with localization loss estimation of 2D and 3D object detectors by addressing the bounding box regression problem, addressing the class imbalance issue affecting the confidence loss estimation, and finally proposing a dynamic cross-model 3D hybrid object detector with enhanced localization and confidence loss estimation.</p><p dir="ltr">This research aims to address challenges in object detectors through four key contributions. In the first part, we aim to address the problems associated with the image classification component of 2D object detectors. Class imbalance is a common problem associated with supervised training. Common causes are noisy data, a scene with a tiny object surrounded by background pixels, or a dense scene with too many objects. These scenarios can produce many negative samples compared to positive ones, affecting the network learning and reducing the overall performance. We examined these drawbacks and proposed an Enhanced Hard Negative Mining (EHNM) approach, which utilizes anchor boxes with 20% to 50% overlap and positive and negative samples to boost performance. The efficiency of the proposed EHNM was evaluated using Single Shot Multibox Detector (SSD) architecture on the PASCAL VOC dataset, indicating that the detection accuracy of tiny objects increased by 3.9% and 4% and the overall accuracy improved by 0.9%. </p><p dir="ltr">To address localization loss, our second approach investigates drawbacks associated with existing bounding box regression problems, such as poor convergence and incorrect regression. We analyzed various cases, such as when objects are inclusive of one another, two objects with the same centres, two objects with the same centres and similar aspect ratios. During our analysis, we observed existing intersections over Union (IoU) loss and its variant’s failure to address them. We proposed two new loss functions, Improved Intersection Over Union (IIoU) and Balanced Intersection Over Union (BIoU), to enhance performance and minimize computational efforts. Two variants of the YOLOv5 model, YOLOv5n6 and YOLOv5s, were utilized to demonstrate the superior performance of IIoU on PASCAL VOC and CGMU datasets. With help of ROS and NVIDIA’s devices, inference speed was observed in real-time. Extensive experiments were performed to evaluate the performance of BIoU on object detectors. The evaluation results indicated MASK_RCNN network trained on the COCO dataset, YOLOv5n6 network trained on SKU-110K and YOLOv5x trained on the custom e-scooter dataset demonstrated 3.70% increase on small objects, 6.20% on 55% overlap and 9.03% on 80% overlap.</p><p dir="ltr">In the earlier parts, we primarily focused on 2D object detectors. Owing to its success, we extended the scope of our research to 3D object detectors in the later parts. The third portion of our research aims to solve bounding box problems associated with 3D rotated objects. Existing axis-aligned loss functions suffer a performance gap if the objects are rotated. We enhanced the earlier proposed IIoU loss by considering two additional parameters: the objects’ Z-axis and rotation angle. These two parameters aid in localizing the object in 3D space. Evaluation was performed on LiDAR and Fusion methods on 3D KITTI and nuScenes datasets.</p><p dir="ltr">Once we addressed the drawbacks associated with confidence and localization loss, we further explored ways to increase the performance of cross-model 3D object detectors. We discovered from previous studies that perception sensors are volatile to harsh environmental conditions, sunlight, and blurry motion. In the final portion of our research, we propose a hybrid 3D cross-model detection network (MAEGNN) equipped with MaskedAuto Encoders 14 (MAE) and Graph Neural Networks (GNN) along with earlier proposed IIoU and ENHM. The performance evaluation on MAEGNN on the KITTI validation dataset and KITTI test set yielded a detection accuracy of 69.15%, 63.99%, 58.46% and 40.85%, 37.37% on 3D pedestrians with overlap of 50%. This developed hybrid detector overcomes the challenges of localization error and confidence estimation and outperforms many state-of-art 3D object detectors for autonomous platforms.</p>

High-efficiency point cloud 3D object detection is important for autonomous driving. 3D object detection based on point cloud data is naturally more complex and difficult than the 2D task based on images. Researchers keep working on improving 3D object detection performance in autonomous driving scenarios recently. In this report, we present our optimized point cloud 3D object detection model based on CenterPoint method. CenterPoint detects centers of objects using a keypoint detector on top of a voxel-based backbone, then regresses to other attributes. On the basis of this, our modified model is featured with an improved Region Proposal Network (RPN) with extended receptive field, an added sub-head that produces an IoU-aware confidence score, as well as box ensemble inference strategies with more accurate predictions. These model enhancements, together with class-balanced data pre-processing, lead to a competitive accuracy of 72.02 mAP on ONCE Validation Split, and 79.09 mAP on ONCE Test Split. Our model gains the fifth place of ICCV 2021 Workshop SSLAD Track 3D Object Detection Challenge. / Högeffektiv punktmoln 3D-objektdetektering är viktig för autonom körning. 3D-objektdetektering baserad på punktmolnsdata är naturligtvis mer komplex och svårare än 2D-uppgiften baserad på bilder. Forskare fortsätter att arbeta med att förbättra 3D-objektdetekteringsprestandan i scenarier för autonom körning nyligen. I den här rapporten presenterar vi vår optimerade 3D-objektdetekteringsmodell baserad på CenterPoint. CenterPoint upptäcker objektcentrum med hjälp av en nyckelpunktsdetektor ovanpå en voxelbaserad ryggrad och går sedan tillbaka till andra attribut. På grundval av detta presenteras vår modifierade modell med ett förbättrat regionförslagsnätverk med utökat receptivt fält, en extra underrubrik som producerar en IoU-medveten konfidenspoäng och ensemblestrategier med mer exakta förutsägelser. Dessa modellförbättringar, tillsammans med klassbalanserad dataförbehandling, leder till en konkurrenskraftig noggrannhet på 72,02 mAP på ONCE Validation Split och 79,09 mAP på ONCE Test Split. Vår modell vinner femteplatsen i ICCV 2021 Workshop SSLAD Track 3D Object Detection Challenge.

Visual object tracking is one of the fundamental problems in computer vision, with a wide number of practical applications in e.g.\ robotics, surveillance etc. Given a video sequence and the target bounding box in the first frame, a tracker is required to find the target in all subsequent frames. It is a challenging problem due to the limited training data available. An object tracker is generally evaluated using two criterias, namely robustness and accuracy. Robustness refers to the ability of a tracker to track for long durations, without losing the target. Accuracy, on the other hand, denotes how accurately a tracker can estimate the target bounding box. Recent years have seen significant improvement in tracking robustness. However, the problem of accurate tracking has seen less attention. Most current state-of-the-art trackers resort to a naive multi-scale search strategy which has fundamental limitations. Thus, in this thesis, we aim to develop a general target estimation component which can be used to determine accurate bounding box for tracking. We will investigate how bounding box estimators used in object detection can be modified to be used for object tracking. The key difference between detection and tracking is that in object detection, the classes to which the objects belong are known. However, in tracking, no prior information is available about the tracked object, other than a single image provided in the first frame. We will thus investigate different architectures to utilize the first frame information to provide target specific bounding box predictions. We will also investigate how the bounding box predictors can be integrated into a state-of-the-art tracking method to obtain robust as well as accurate tracking.

This thesis investigates predicting the Intersection over Union (IoU) in detections made by the face detector YOLO5Face, which is done to use the predicted IoU as a new uncertainty measure. The detections are done on the face dataset WIDER FACE, and the prediction of IoU is made by adding a parallel head to the existing YOLO5Face architecture. Experiments show that the methodology for predicting the IoU used in this thesis does not work and the parallel prediction head fails to predict the IoU and instead resorts to predicting common IoU values. The localisation confidence and classification confidences of YOLO5Face are then investigated to find out which confidence measure is least uncertain and most suitable to use when identifying faces. Experiments show that the localisation confidence is consistently more calibrated than the classification confidence. The classification confidence is then calibrated with respect to the localisation confidence which reduces the Expected Calibration Error (ECE) for classification confidence from 0.17 to 0.01.

Les promesses de payer sont des contrats par lesquels une personne s’engage envers un créancier à payer ce qui lui est dû. De tels actes sont courants ; leurs applications sont variées. Le cautionnement, l’acceptation d’une lettre de change, la promesse d’exécuter une obligation naturelle, l’engagement du délégué envers le délégataire, le constitut, la garantie autonome, la souscription d’un billet à ordre, etc., sont des promesses de payer. Plus précisément, ces actes sont des applications diverses d’une même figure juridique : la promesse de payer. Cette dernière, déshabillée des particularités propres à chacune de ses applications spéciales, se présente comme une figure juridique unitaire, pourvue d’une nature et de caractères permanents. Ayant pour objet un paiement, elle suppose toujours l’existence d’une dette à acquitter. Cette dette, ou « obligation principale », constitue sa cause objective. Contrairement à une simple reconnaissance de dette, la promesse ne se borne pas à déclarer l’existence de celle-ci. En tant qu’engagement d’exécution, elle donne naissance à une nouvelle obligation, l’ « obligation de règlement », venant s’adjoindre à la première en vue de son paiement. L’obligation de règlement, à ce titre, constitue l’accessoire de l’obligation principale. Son régime, de sa naissance à son extinction, sera donc plus ou moins lié à celui de cette dernière. / Promises to pay are contracts by which a person commits to pay to a creditor what is owed to him. Such acts are as common as they are various. For instance, bond, acceptance of a bill of exchange, promise to perform a natural obligation, commitment of the delegate to the delegatee, autonomous guarantee, subscription of a promissory note, etc. are promises to pay. In fact, such acts are different applications of a single legal figure : the promise to pay. Apart from the specificities of each of its applications, the promise to pay reveals itself as a uniform legal act with a permanent nature. Because its subject consists in a payment, the promise to pay always presupposes the existence of a debt. Such debt, or “primary obligation”, is the “objective cause” of the promise. Unlike a simple “IOU”, a promise to pay is not limited to declare the existence of the primary obligation. As a commitment, it also produces a new obligation, the “obligation to pay”, which coexists with the primary obligation. The obligation to pay, as such, is ancillary to the primary obligation. Its legal status, from its birth to its expiration, will be closely linked to that of the primary obligation.