In this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. Most successful approaches for re-identification involve (deep) learning an embedding space such that the vehicles of same identities are projected closer to one another, compared to the vehicles representing different identities. Popular loss functions for learning an embedding (space) include contrastive or triplet loss. In this paper we provide an extensive evaluation of these losses applied to vehicle re-identification and demonstrate that using the best practices for learning embeddings outperform most of the previous approaches proposed in the vehicle re-identification literature. Compared to most existing state-of-the-art approaches, our approach is simpler and more straightforward for training utilizing only identity-level annotations, along with one of the smallest published embedding dimensions for efficient inference. Furthermore in this work we introduce a formal evaluation of a triplet sampling variant (batch sample) into the re-identification literature.

We present a novel fuzzy approach for the task of detecting buildings in monocular greyscale imagery in the form of our system FuzzBuRS. Our approach rigorously addresses the problem of uncertainty and imprecision that exists within the building recognition scenario. Fuzzy variables are used for representing various types of building evidence, such as significant straight edges and homogeneous regions. These variables and fuzzy if/then rules allow for a fuzzy reasoning system that assigns possibilities to building hypotheses. FuzzBuRS demonstrates the potential of a fuzzy approach to the building recognition task. This system has a compact representation and is easily understandable.

The paper motivates and presents a new fuzzy approach to the task of recognizing buildings in monocular greyscale aerial images. We motivate our fuzzy system, FuzzBuRS, by demonstrating that the building recognition task is an approximately formulated problem. We also show that building recognition systems are capable of taking advantage of machine learning techniques and propose learning extensions to our system.

The abrupt boundary truncation of an image introduces artifacts in the restored image. The traditional solution is to smooth the image data using special window functions such as Hamming or trapezoidal windows. This is followed by zero-padding and linear convolution with the restoration filter. This method improves the results but still distorts the image, especially at the margins. Instead of the above method, we propose a different procedure. This procedure is simple and exploits the natural property of "circular" or periodic convolution of the discrete Fourier transform (DFT). Instead of padding the image by zeros, it is padded by a reflected version of it. This is followed by "circular" convolution with the restoration filter. This procedure is shown to lead to better restoration results than the windowing and linear convolution techniques. The computational effort is also improved since our method requires half the number of computations required by the conventional linear deconvolution method.