Improving the fire retardancy of extruded/coextruded wood-plastic composites

The main objective of this thesis is to study the impact of different mineral fillers and fire retardants on the reaction-to-fire properties of extruded/coextruded wood-plastic composites (WPCs). The impact of additives on the flammability properties of WPCs is studied by cone calorimetry. The studied properties are ignition time, peak heat release rate, total heat release, total smoke production, and mass loss rate. The effects of mineral fillers and fire retardants were found to vary with the type of additive, the type of additive combinations, the amount of additives, as well as the production method of the WPCs. The study shows that talc can be used to improve the properties of extruded WPCs. Especially ignition time, peak heat release rate and mass loss rate were found to be improved significantly by talc. The most significant improvement in the fire retardancy of coextruded WPCs was achieved in combinations of natural graphite and melamine. Ignition time, peak heat release rate and total smoke production were improved essentially. High increase in smoke production was found in samples where the amount of ammonium polyphosphate was 10% or higher. Coextrusion as a structural modification was found as a promising way to improve the flammability properties of composite materials in a cost-effective way.

Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.