Browsing by Subject "computer vision"

Sort by: Order: Results:

Now showing items 1-9 of 9
  • Khoramshahi, Ehsan; Campos, Mariana Batista; Tommaselli , Antonio Maria Garcia; Vilijanen, Niko; Mielonen , Teemu; Kaartinen, Harri; Kukko, Antero; Honkavaara, Eija (2019)
    Mobile mapping systems (MMS) are increasingly used for many photogrammetric and computer vision applications, especially encouraged by the fast and accurate geospatial data generation. The accuracy of point position in an MMS is mainly dependent on the quality of calibration, accuracy of sensor synchronization, accuracy of georeferencing and stability of geometric configuration of space intersections. In this study, we focus on multi-camera calibration (interior and relative orientation parameter estimation) and MMS calibration (mounting parameter estimation). The objective of this study was to develop a practical scheme for rigorous and accurate system calibration of a photogrammetric mapping station equipped with a multi-projective camera (MPC) and a global navigation satellite system (GNSS) and inertial measurement unit (IMU) for direct georeferencing. The proposed technique is comprised of two steps. Firstly, interior orientation parameters of each individual camera in an MPC and the relative orientation parameters of each cameras of the MPC with respect to the first camera are estimated. In the second step the offset and misalignment between MPC and GNSS/IMU are estimated. The global accuracy of the proposed method was assessed using independent check points. A correspondence map for a panorama is introduced that provides metric information. Our results highlight that the proposed calibration scheme reaches centimeter-level global accuracy for 3D point positioning. This level of global accuracy demonstrates the feasibility of the proposed technique and has the potential to fit accurate mapping purposes
  • Ärje, Johanna; Melvad, Claus; Jeppesen, Mads Rosenhoj; Madsen, Sigurd Agerskov; Raitoharju, Jenni; Rasmussen, Maria Strandgård; Iosifidis, Alexandros; Tirronen, Ville; Gabbouj, Moncef; Meissner, Kristian; Hoye, Toke Thomas (British Ecological Society, 2020)
    Methods in Ecology and Evolution 11 8 (2020)
    1. Understanding how biological communities respond to environmental changes is a key challenge in ecology and ecosystem management. The apparent decline of insect populations necessitates more biomonitoring but the time-consuming sorting and expert-based identification of taxa pose strong limitations on how many insect samples can be processed. In turn, this affects the scale of efforts to map and monitor invertebrate diversity altogether. Given recent advances in computer vision, we propose to enhance the standard human expert-based identification approach involving manual sorting and identification with an automatic image-based technology. 2. We describe a robot-enabled image-based identification machine, which can automate the process of invertebrate sample sorting, specimen identification and biomass estimation. We use the imaging device to generate a comprehensive image database of terrestrial arthropod species which is then used to test classification accuracy, that is, how well the species identity of a specimen can be predicted from images taken by the machine. We also test sensitivity of the classification accuracy to the camera settings (aperture and exposure time) to move forward with the best possible image quality. We use state-of-the-art Resnet-50 and InceptionV3 convolutional neural networks for the classification task. 3. The results for the initial dataset are very promising as we achieved an average classification accuracy of 0.980. While classification accuracy is high for most species, it is lower for species represented by less than 50 specimens. We found significant positive relationships between mean area of specimens derived from images and their dry weight for three species of Diptera. 4. The system is general and can easily be used for other groups of invertebrates as well. As such, our results pave the way for generating more data on spatial and temporal variation in invertebrate abundance, diversity and biomass.
  • Laitala, Julius (Helsingin yliopisto, 2021)
    Arranging products in stores according to planograms, optimized product arrangement maps, is important for keeping up with the highly competitive modern retail market. The planograms are realized into product arrangements by humans, a process which is prone to mistakes. Therefore, for optimal merchandising performance, the planogram compliance of the arrangements needs to be evaluated from time to time. We investigate utilizing a computer vision problem setting – retail product detection – to automate planogram compliance evaluation. We introduce the relevant problems, the state-of- the-art approaches for solving them and background information necessary for understanding them. We then propose a computer vision based planogram compliance evaluation pipeline based on the current state of the art. We build our proposed models and algorithms using PyTorch, and run tests against public datasets and an internal dataset collected from a large Nordic retailer. We find that while the retail product detection performance of our proposed approach is quite good, the planogram compliance evaluation performance of our whole pipeline leaves a lot of room for improvement. Still, our approach seems promising, and we propose multiple ways for improving the performance enough to enable possible real world utility. The code used for our experiments and the weights for our models are available at
  • Chumachenko, Kateryna; Männistö, Anssi; Iosifidis, Alexandros; Raitoharju, Jenni (IEEE, 2020)
    IEEE Access 8 (2020)
    In this paper, we demonstrate the benefits of using state-of-the-art machine learning methods in the analysis of historical photo archives. Specifically, we analyze prominent Finnish World War II photographers, who have captured high numbers of photographs in the publicly available Finnish Wartime Photograph Archive, which contains 160,000 photographs from Finnish Winter, Continuation, and Lapland Wars captures in 1939-1945. We were able to find some special characteristics for different photographers in terms of their typical photo content and framing (e.g., close-ups vs. overall shots, number of people). Furthermore, we managed to train a neural network that can successfully recognize the photographer from some of the photos, which shows that such photos are indeed characteristic for certain photographers. We further analyzed the similarities and differences between the photographers using the features extracted from the photographer classifier network. We make our annotations and analysis pipeline publicly available, in an effort to introduce this new research problem to the machine learning and computer vision communities and facilitate future research in historical and societal studies over the photo archives.
  • Leinonen, Matti (Helsingin yliopisto, 2021)
    3D Object detection and tracking are computer vision methods used in many applications. It is necessary for autonomous vehicles and robots to be able to reliably extract 3D localization information about objects in their environment to operate safely. Currently most 3D object detection and tracking algorithms use high quality LiDAR-sensors which are very expensive. This is why research into methods that use cheap monocular camera images as inputs is an active field in computer vision research. Most current research into monocular 3D object detection and tracking is focused in autonomous driving. This thesis investigates how well current monocular methods are suited for use in industrial settings where the environment and especially the camera perspective can be very different compared to what it is in an automobile. This thesis introduces some of the most used 3D object detection and tracking methods and techniques and tests one detection method on a dataset where the environment and the point of view differs from what it would be in autonomous driving. This thesis also analyzes the technical requirements for a detection and tracking system that could be be used for autonomous robots in an industrial setting and what future research would be necessary to develop such a system.
  • Kutvonen, Konsta (Helsingin yliopisto, 2020)
    With modern computer vision algorithms, it is possible to solve many different kinds of problems, such as object detection, image classification, and image segmentation. In some cases, like in the case of a camera-based self-driving car, the task can't yet be adequately solved as a direct mapping from image to action with a single model. In such situations, we need more complex systems that can solve multiple computer vision tasks to understand the environment and act based on it for acceptable results. Training each task on their own can be expensive in terms of storage required for all weights and especially for the inference time as the output of several large models is needed. Fortunately, many state-of-the-art solutions to these problems use Convolutional Neural Networks and often feature some ImageNet backbone in their architecture. With multi-task learning, we can combine some of the tasks into a single model, sharing the convolutional weights in the network. Sharing the weights allows for training smaller models that produce outputs faster and require less computational resources, which is essential, especially when the models are run on embedded devices with constrained computation capability and no ability to rely on the cloud. In this thesis, we will present some state-of-the-art models to solve image classification and object detection problems. We will define multi-task learning, how we can train multi-task models, and take a look at various multi-task models and how they exhibit the benefits of multi-task learning. Finally, to evaluate how training multi-task models changes the basic training paradigm and to find what issues arise, we will train multiple multi-task models. The models will mainly focus on image classification and object detection using various data sets. They will combine multiple tasks into a single model, and we will observe the impact of training the tasks in a multi-task setting.
  • Holmstrom, Oscar; Linder, Nina; Ngasala, Billy; Martensson, Andreas; Linder, Ewert; Lundin, Mikael; Moilanen, Hannu; Suutala, Antti; Diwan, Vinod; Lundin, Johan (2017)
    Background: Microscopy remains the gold standard in the diagnosis of neglected tropical diseases. As resource limited, rural areas often lack laboratory equipment and trained personnel, new diagnostic techniques are needed. Low-cost, point-of-care imaging devices show potential in the diagnosis of these diseases. Novel, digital image analysis algorithms can be utilized to automate sample analysis. Objective: Evaluation of the imaging performance of a miniature digital microscopy scanner for the diagnosis of soil-transmitted helminths and Schistosoma haematobium, and training of a deep learning-based image analysis algorithm for automated detection of soil-transmitted helminths in the captured images. Methods: A total of 13 iodine-stained stool samples containing Ascaris lumbricoides, Trichuris trichiura and hookworm eggs and 4 urine samples containing Schistosoma haematobium were digitized using a reference whole slide-scanner and the mobile microscopy scanner. Parasites in the images were identified by visual examination and by analysis with a deep learning-based image analysis algorithm in the stool samples. Results were compared between the digital and visual analysis of the images showing helminth eggs. Results: Parasite identification by visual analysis of digital slides captured with the mobile microscope was feasible for all analyzed parasites. Although the spatial resolution of the reference slide-scanner is higher, the resolution of the mobile microscope is sufficient for reliable identification and classification of all parasites studied. Digital image analysis of stool sample images captured with the mobile microscope showed high sensitivity for detection of all helminths studied (range of sensitivity = 83.3-100%) in the test set (n = 217) of manually labeled helminth eggs. Conclusions: In this proof-of-concept study, the imaging performance of a mobile, digital microscope was sufficient for visual detection of soil-transmitted helminths and Schistosoma haematobium. Furthermore, we show that deep learning-based image analysis can be utilized for the automated detection and classification of helminths in the captured images.
  • Hiippala, Tuomo (IEEE, 2017)
    This paper presents a system that uses machine learning to recognize military vehicles in social media images. To do so, the system draws on recent advances in applying deep neural networks to computer vision tasks, while also making extensive use of openly available libraries, models and data. Training a vehicle recognition system over three classes, the paper reports on two experiments that use different architectures and strategies to overcome the challenges of working with limited training data: data augmentation and transfer learning. The results show that transfer learning outperforms data augmentation, achieving an average accuracy of 95.18% using 10-fold cross-validation, while also generalizing well on a separate testing set consisting of social media content.
  • Goriachev, Vladimir (Helsingin yliopisto, 2018)
    In the case of remote inspection and maintenance operations, the quality and amount of information available to the operator on demand plays a significant role. In knowledge-intensive tasks performed remotely or in a hazardous environment, augmented and virtual reality technologies are often seen as a solution capable of providing the required level of information support. Application of these technologies faced many obstacles over the years, mostly due to the insufficient maturity level of their technical implementations. This thesis contains a description of the research work related to the usage of augmented and virtual reality in remote inspection and maintenance operations, and is aimed at solving some of the most common problems associated with the application of these technologies. During the project, an optical see-through augmented reality glasses calibration method was developed, as well as a virtual reality application for robotic teleoperation. The implemented teleoperation system was tested in two different simulated scenarios, and the additional questions of the immersive environment reconstruction, spatial user interface, connection between virtual and real worlds are addressed in this thesis report.