Filtering by
- Member of: Theses and Dissertations
Content detection on handwritten documents assigns a particular class to a homogeneous portion of the document. To complete this task, a set of handwritten solutions was digitally collected from middle school students located in two different geographical regions in 2017 and 2018. This research discusses the methods to collect, pre-process and detect content type in the collected handwritten documents. A total of 4049 documents were extracted in the form of image, and json format; and were labelled using an object labelling software with tags being text, math, diagram, cross out, table, graph, tick mark, arrow, and doodle. The labelled images were fed to the Tensorflow’s object detection API to learn a neural network model. We show our results from two neural networks models, Faster Region-based Convolutional Neural Network (Faster R-CNN) and Single Shot detection model (SSD).
This thesis proposes a novel evaluation framework that analyses the performance of popular existing object proposal generators in detecting the most salient objects. This work also shows that, by incorporating saliency constraints, the number of generated object proposals and thus the computational cost can be decreased significantly for a target true positive detection rate (TPR).
As part of the proposed framework, salient ground-truth masks are generated from the given original ground-truth masks for a given dataset. Given an object detection dataset, this work constructs salient object location ground-truth data, referred to here as salient ground-truth data for short, that only denotes the locations of salient objects. This is obtained by first computing a saliency map for the input image and then using it to assign a saliency score to each object in the image. Objects whose saliency scores are sufficiently high are referred to as salient objects. The detection rates are analyzed for existing object proposal generators with respect to the original ground-truth masks and the generated salient ground-truth masks.
As part of this work, a salient object detection database with salient ground-truth masks was constructed from the PASCAL VOC 2007 dataset. Not only does this dataset aid in analyzing the performance of existing object detectors for salient object detection, but it also helps in the development of new object detection methods and evaluating their performance in terms of successful detection of salient objects.
Today, Computer Vision has become ubiquitous in our society with several in image understanding, medicine, drones, self-driving cars and many more. With the advent of GPUs and the availability of huge datasets like ImageNet, Convolutional Neural Networks (CNNs) have come to play a very important role in solving computer vision tasks, e.g object detection. However, the size of the networks become
prohibitive when higher accuracies are needed, which in turn demands more hardware. This hinders the application of CNNs to mobile platforms and stops them from hitting the real-time mark. The computational efficiency of a computer vision task, like object detection, can be enhanced by adopting a selective attention mechanism into the algorithm. In this work, this idea is explored by using Visual Proto Object Saliency algorithm [1] to crop out the areas of an image without relevant objects before a computationally intensive network like the Faster R-CNN [2] processes it.
In the context of varying illumination, this work focuses on robust generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS) under varying illumination conditions. The highlight of the first method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). It is first shown that the angular distortion in the Inverse Perspective Mapping (IPM) domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. This information is used to generate object proposals. A novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction is also proposed.
In the context of image quality, this work focuses on robust multiple-class object detection using deep neural networks for images with varying quality. The use of Generative Adversarial Networks (GANs) is proposed in a novel generative framework to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher object detection and classification accuracy compared to the existing approaches.
Testing autonomous vehicles in real-world scenarios would pose a threat to people and property alike. A safe alternative is to simulate these scenarios and test to ensure that the resulting programs can work in real-world scenarios. Moreover, in order to detect a moral dilemma situation quickly, the vehicle should be able to identify objects in real-time while driving. Toward this end, this thesis investigates the use of cross-platform training for neural networks that perform visual identification of common objects in driving scenarios. Here, the object detection algorithm Faster R-CNN is used. The hypothesis is that it is possible to train a neural network model to detect objects from two different domains, simulated or physical, using transfer learning. As a proof of concept, an object detection model is trained on image datasets extracted from CARLA, a virtual driving environment, via transfer learning. After bringing the total loss factor to 0.4, the model is evaluated with an IoU metric. It is determined that the model has a precision of 100% and 75% for vehicles and traffic lights respectively. The recall is found to be 84.62% and 75% for the same. It is also shown that this model can detect the same classes of objects from other virtual environments and real-world images. Further modifications to the algorithm that may be required to improve performance are discussed as future work.
With the rapid increase of technological capabilities, particularly in processing power and speed, the usage of machine learning is becoming increasingly widespread, especially in fields where real-time assessment of complex data is extremely valuable. This surge in popularity of machine learning gives rise to an abundance of potential research and projects on further broadening applications of artificial intelligence. From these opportunities comes the purpose of this thesis. Our work seeks to meaningfully increase our understanding of current capabilities of machine learning and the problems they can solve. One extremely popular application of machine learning is in data prediction, as machines are capable of finding trends that humans often miss. Our effort to this end was to examine the CVE dataset and attempt to predict future entries with Random Forests. The second area of interest lies within the great promise being demonstrated by neural networks in the field of autonomous driving. We sought to understand the research being put out by the most prominent bodies within this field and to implement a model on one of the largest standing datasets, Berkeley DeepDrive 100k. This thesis describes our efforts to build, train, and optimize a Random Forest model on the CVE dataset and a convolutional neural network on the Berkeley DeepDrive 100k dataset. We document these efforts with the goal of growing our knowledge on (and usage of) machine learning in these topics.