Abstract: This work compares Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) deep neural networks for the outdoor advertisement panel detection problem by handling multiple and combined variabilities in the scenes. Publicity panel detection in images offers important advantages both in the real world as well as in the virtual one. For example, applications like Google Street View can be used for Internet publicity and when detecting these ads panels in images, it could be possible to replace the publicity appearing inside the panels by another from a funding company. In our experiments, both SSD and YOLO detectors have produced acceptable results under variable sizes of panels, illumination conditions, viewing perspectives, partial occlusion of panels, complex background and multiple panels in scenes. Due to the difficulty of finding annotated images for the considered problem, we created our own dataset for conducting the experiments. The major strength of the SSD model was the almost elimination of False Positive (FP) cases, situation that is preferable when the publicity contained inside the panel is analyzed after detecting them. On the other side, YOLO produced better panel localization results detecting a higher number of True Positive (TP) panels with a higher accuracy. Finally, a comparison of the two analyzed object detection models with different types of semantic segmentation networks and using the same evaluation metrics is also included.

Abstract: Recent breakthroughs in single image super resolution have investigated the potential of deep Convolutional Neural Networks (CNNs) to improve performance. However, CNNs based models suffer from their limited fields and their inability to adapt to the input content. Recently, Transformer based models were presented, which demonstrated major performance gains in Natural Language Processing and Vision tasks while mitigating the drawbacks of CNNs. Nevertheless, Transformer computational complexity can increase quadratically for high-resolution images, and the fact that it ignores the original structures of the image by converting them to the 1D structure can make it problematic to capture the local context information and adapt it for real-time applications. In this paper, we present, SRFormer, an efficient yet powerful Transformer-based architecture, by making several key designs in the building of Transformer blocks and Transformer layers that allow us to consider the original structure of the image (i.e., 2D structure) while capturing both local and global dependencies without raising computational demands or memory consumption. We also present a Gated Multi-Layer Perceptron (MLP) Feature Fusion module to aggregate the features of different stages of Transformer blocks by focusing on inter-spatial relationships while adding minor computational costs to the network. We have conducted extensive experiments on several super-resolution benchmark datasets to evaluate our approach. SRFormer demonstrates superior performance compared to state-of-the-art methods from both Transformer and Convolutional networks, with an improvement margin of 0.1∼0.53dB . Furthermore, while SRFormer has almost the same model size, it outperforms SwinIR by 0.47% and inference time by half the time of SwinIR. The code will be available on GitHub.

Abstract: Current CNN-based stereo depth estimation models can barely run under real-time constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art evaluations usually do not consider model optimization techniques, being that it is unknown what is the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models on three different embedded GPU devices, with and without optimization methods, presenting performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically augmenting the runtime speed of current models. In our experiments, we achieve real-time inference speed, in the range of 5–32 ms, for 1216 × 368 input stereo images on the Jetson TX2, Jetson Xavier, and Jetson Nano embedded devices.