Object detection and recognition algorithms using deep convolutional neural networks (CNNs) tend to be computationally intensive to implement. This presents a particular challenge for embedded systems, such as mobile robots, where the computational resources tend to be far less than for workstations. As an alternative to standard, uniformly sampled images, we propose the use of foveated image sampling here to reduce the size of images, which are faster to process in a CNN due to the reduced number of convolution operations. We evaluate object detection and recognition on the Microsoft COCO database, using foveated image sampling at different image sizes, ranging from 416x416 to 96x96 pixels, on an embedded GPU -- an NVIDIA Jetson TX2 with 256 CUDA cores. The results show that it is possible to achieve a 4x speed-up in frame rates, from 3.59 FPS to 15.24 FPS, using 416x416 and 128x128 pixel images respectively. For foveated sampling, this image size reduction led to just a small decrease in recall performance in the foveal region, to 92.0% of the baseline performance with full-sized images, compared to a significant decrease to 50.1% of baseline recall performance in uniformly sampled images, demonstrating the advantage of foveated sampling.
Efficient processing of high-res video streams is safety-critical for many robotics applications such as autonomous driving. To maintain real-time performance, many practical systems downsample the video stream. But this can hurt downstream tasks such as (small) object detection. Instead, we take inspiration from biological vision systems that allocate more foveal "pixels" to salient parts of the scene. We introduce FOVEA, an approach for intelligent downsampling that ensures salient image regions remain "magnified" in the downsampled output. Given a high-res image, FOVEA applies a differentia…
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）
We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We develop a multitask model for both Object Detection and Semantic Segmentation and analyze the challenges that appear during its training. Our multitask network is 1.6x faster, lighter and uses less memory than deploying the single-task models in parallel. We conclude that MTL has the potential to give superior performance in exchange of a more complex training…
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications. However, real-time scene parsing through object detection running on a UAV platform is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, in this paper we propose to learn efficient deep object detectors through channel pruning of convolutional layers. To this end, we enforce channel-level sparsity of convolutional layers by imposing L1 regularization o…
The last few years have brought advances in computer vision at an amazing pace, grounded on new findings in deep neural network construction and training as well as the availability of large labeled datasets. Applying these networks to images demands a high computational effort and pushes the use of state-of-the-art networks on real-time video data out of reach of embedded platforms. Many recent works focus on reducing network complexity for real-time inference on embedded computing platforms. We adopt an orthogonal viewpoint and propose a novel algorithm exploiting the spatio-temporal sparsit…
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
Transfer learning is one of the subjects undergoing intense study in the area of machine learning. In object recognition and object detection there are known experiments for the transferability of parameters, but not for neural networks which are suitable for object detection in real time embedded applications, such as the SqueezeDet neural network. We use transfer learning to accelerate the training of SqueezeDet to a new group of classes. Also, experiments are conducted to study the transferability and co-adaptation phenomena introduced by the transfer learning process. To accelerate trainin…
Chongqing University of Science and Technology（重庆科技学院）
Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes. To solve this problem, in this paper, we propose a novel lightweight deep learning architectures named FasterX based on YOLOX model for real-time object detection on edge GPU. First, we design an effective and lightweight PixSF head to replace the original head of YOLOX to better detect small objects, which can be further embedded in the depthwise separable convolution (DS Conv) to achieve a lighter head. Then, a slim…
Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））；Sharif University of Technology（谢里夫理工大学）；Universitat de Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
Medical image segmentation has been very challenging due to the large variation of anatomy across different cases. Recent advances in deep learning frameworks have exhibited faster and more accurate performance in image segmentation. Among the existing networks, U-Net has been successfully applied on medical image segmentation. In this paper, we propose an extension of U-Net for medical image segmentation, in which we take full advantages of U-Net, Squeeze and Excitation (SE) block, bi-directional ConvLSTM (BConvLSTM), and the mechanism of dense convolutions. (I) We improve the segmentation pe…
Idiap Research Institute（Idiap 研究所）；EPFL（洛桑联邦理工学院）；University of Geneva（日内瓦大学）
Semantic segmentation is a well-addressed topic in the computer vision literature, but the design of fast and accurate video processing networks remains challenging. In addition, to run on embedded hardware, computer vision models often have to make compromises on accuracy to run at the required speed, so that a latency/accuracy trade-off is usually at the heart of these real-time systems' design. For the specific case of videos, models have the additional possibility to make use of computations made for previous frames to mitigate the accuracy loss while being real-time. In this work, we prop…
Recent advancements in parallel computing, GPU technology and deep learning provide a new platform for complex image processing tasks such as person detection to flourish. Person detection is fundamental preliminary operation for several high level computer vision tasks. One industry that can significantly benefit from person detection is retail. In recent years, various studies attempt to find an optimal solution for person detection using neural networks and deep learning. This study conducts a comparison among the state of the art deep learning base object detector with the focus on person …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Inspirit IoT, Inc（英斯匹特物联网公司）；IBM Research（IBM研究院）
Object detection and tracking are challenging tasks for resource-constrained embedded systems. While these tasks are among the most compute-intensive tasks from the artificial intelligence domain, they are only allowed to use limited computation and memory resources on embedded devices. In the meanwhile, such resource-constrained implementations are often required to satisfy additional demanding requirements such as real-time response, high-throughput performance, and reliable inference accuracy. To overcome these challenges, we propose SkyNet, a hardware-efficient neural network to deliver th…
University of Warsaw（华沙大学）；Purdue University（普渡大学）
The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point operations and have long run-times that hinder their usability. In this paper, we propose a novel deep neural network architecture named ENet (efficient neural network), created specifically for tasks requiring low latency operation. ENet is up to 18$\times$ faster, requires 75$\times$ less FLOPs, has 79$\times$ less parameters, and provides similar or better acc…
The field of view (FOV) of convolutional neural networks is highly related to the accuracy of inference. Dilated convolutions are known as an effective solution to the problems which require large FOVs. However, for general-purpose hardware or dedicated hardware, it usually takes extra time to handle dilated convolutions compared with standard convolutions. In this paper, we propose a network module, Cascaded and Separable Structure of Dilated (CASSOD) Convolution, and a special hardware system to handle the CASSOD networks efficiently. A CASSOD-Net includes multiple cascaded $2 \times 2$ dila…
Deep learning architectures are an extremely powerful tool for recognizing and classifying images. However, they require supervised learning and normally work on vectors the size of image pixels and produce the best results when trained on millions of object images. To help mitigate these issues, we propose the fusion of bottom-up saliency and top-down attention employing only unsupervised learning techniques, which helps the object recognition module to focus on relevant data and learn important features that can later be fine-tuned for a specific task. In addition, by utilizing only relevant…
The Technical University of Kenya（肯尼亚技术大学）；IRISA（法国国家信息与自动化研究所雷恩分院（IRISA））；Université Bretagne Sud（南布列塔尼大学）
Deep-learning-based image classification and object detection has been applied successfully to tree monitoring. However, studies of tree crowns and fallen trees, especially on flood inundated areas, remain largely unexplored. Detection of degraded tree trunks on natural environments such as water, mudflats, and natural vegetated areas is challenging due to the mixed colour image backgrounds. In this paper, Unmanned Aerial Vehicles (UAVs), or drones, with embedded RGB cameras were used to capture the fallen Acacia Xanthophloea trees from six designated plots around Lake Nakuru, Kenya. Motivated…
With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks have resulted in low-footprint, highly-efficient, self-attention neural networks that strike a strong balance between accuracy and speed. In this study, we introduce a faster attention condenser design called double-condensing attention condensers that allow for highly condensed feature embeddings. We further employ a machine-driven design exploration strat…
The recent introduction of powerful embedded graphics processing units (GPUs) has allowed for unforeseen improvements in real-time computer vision applications. It has enabled algorithms to run onboard, well above the standard video rates, yielding not only higher information processing capability, but also reduced latency. This work focuses on the applicability of efficient low-level, GPU hardware-specific instructions to improve on existing computer vision algorithms in the field of visual-inertial odometry (VIO). While most steps of a VIO pipeline work on visual features, they rely on image…
Canon Inc.（佳能公司）；Canon Information Technology (Beijing) Co., Ltd. (CIB)（佳能信息技术（北京）有限公司）
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks for embedded-computer-vision algorithms. Different from related works, the proposed architecture can support filter kernels with different sizes with high flexibility since it does not require extra costs for intra-kernel parallelism, and it can generate convolution results faster than the architecture of the related works. The experimental results show the…
We propose Image-Semantic-Transformation-Reconstruction-Circle(ISTRC) model, a novel and powerful method using facenet's Euclidean latent space to understand the images. As the name suggests, ISTRC construct the circle, able to perfectly reconstruct images. One powerful Euclidean latent space embedded in ISTRC is FaceNet's last layer with the power of distinguishing and understanding images. Our model will reconstruct the images and manipulate Euclidean latent vectors to achieve semantic transformations and semantic images arthimetic calculations. In this paper, we show that ISTRC performs 10 …
Currently, most image quality assessment (IQA) models are supervised by the MAE or MSE loss with empirically slow convergence. It is well-known that normalization can facilitate fast convergence. Therefore, we explore normalization in the design of loss functions for IQA. Specifically, we first normalize the predicted quality scores and the corresponding subjective quality scores. Then, the loss is defined based on the norm of the differences between these normalized values. The resulting "Norm-in-Norm'' loss encourages the IQA model to make linear predictions with respect to subjective qualit…
Global covariance pooling in convolutional neural networks has achieved impressive improvement over the classical first-order pooling. Recent works have shown matrix square root normalization plays a central role in achieving state-of-the-art performance. However, existing methods depend heavily on eigendecomposition (EIG) or singular value decomposition (SVD), suffering from inefficient training due to limited support of EIG and SVD on GPU. Towards addressing this problem, we propose an iterative matrix square root normalization method for fast end-to-end training of global covariance pooling…
Mobile and embedded platforms are increasingly required to efficiently execute computationally demanding DNNs across heterogeneous processing elements. At runtime, the available hardware resources to DNNs can vary considerably due to other concurrently running applications. The performance requirements of the applications could also change under different scenarios. To achieve the desired performance, dynamic DNNs have been proposed in which the number of channels/layers can be scaled in real time to meet different requirements under varying resource constraints. However, the training process …
University of Surrey（萨里大学）；National Physical Laboratory（英国国家物理实验室）
The usage of chemical imaging technologies is becoming a routine accompaniment to traditional methods in pathology. Significant technological advances have developed these next generation techniques to provide rich, spatially resolved, multidimensional chemical images. The rise of digital pathology has significantly enhanced the synergy of these imaging modalities with optical microscopy and immunohistochemistry, enhancing our understanding of the biological mechanisms and progression of diseases. Techniques such as imaging mass cytometry provide labelled multidimensional (multiplex) images of…
Depth sensing is a critical function for robotic tasks such as localization, mapping and obstacle detection. There has been a significant and growing interest in depth estimation from a single RGB image, due to the relatively low cost and size of monocular cameras. However, state-of-the-art single-view depth estimation algorithms are based on fairly complex deep neural networks that are too slow for real-time inference on an embedded platform, for instance, mounted on a micro aerial vehicle. In this paper, we address the problem of fast depth estimation on embedded systems. We propose an effic…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shandong University of Science and Technology（山东科技大学）；Artificial Intelligence Research, Chinese Academy of Sciences（中国科学院人工智能研究院）
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and over-parameterized. The low efficiency in model training and inference has increased the validation costs of model architectures in large-scale datasets. To address the above issue, recent advanced separable convolutional layers are embedded into an early fused Multiple Input Branches (MIB) network, constructing an efficient Graph Convolutional N…
It is always well believed that Binary Neural Networks (BNNs) could drastically accelerate the inference efficiency by replacing the arithmetic operations in float-valued Deep Neural Networks (DNNs) with bit-wise operations. Nevertheless, there has not been open-source implementation in support of this idea on low-end ARM devices (e.g., mobile phones and embedded devices). In this work, we propose daBNN --- a super fast inference framework that implements BNNs on ARM devices. Several speed-up and memory refinement strategies for bit-packing, binarized convolution, and memory layout are uniquel…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）
Access to 3D point cloud representations has been widely facilitated by LiDAR sensors embedded in various mobile devices. This has led to an emerging need for fast and accurate point cloud processing techniques. In this paper, we revisit and dive deeper into PointNet++, one of the most influential yet under-explored networks, and develop faster and more accurate variants of the model. We first present a novel Separable Set Abstraction (SA) module that disentangles the vanilla SA module used in PointNet++ into two separate learning stages: (1) learning channel correlation and (2) learning spati…
Building Information Modeling (BIM) is increasingly used in the construction industry, but existing studies often ignore embedded rebars. Ground Penetrating Radar (GPR) provides a potential solution to develop as-built BIM with surface elements and rebars. However, automatically translating rebars from GPR into BIM is challenging since GPR cannot provide any information about the scanned element. Thus, we propose an approach to link GPR data and BIM according to Faster R-CNN. A label is attached to each element scanned by GPR for capturing the labeled images, which are used with other images t…
3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on embedded systems from the perspective of latency and power efficiency. For high speed driving scenarios, latency is a crucial parameter as it provides more time to react to dangerous situations. Typically a voxel or point-cloud based 3D convolution approach is utilized for this module. Firstly, they are inefficient on embedded platforms as they are not suit…
CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition
National Formosa University（国立虎尾科技大学）；University of Muhammadiyah Malang（马朗穆罕默迪亚大学）；National Taiwan University of Science and Technology（台湾科技大学）；National Yang Ming Chiao Tung University（国立阳明交通大学）
HKUST Robotics Institute（香港科技大学机器人研究所）；ATG Robotics；University of Bristol（布里斯托大学）；Aristotle University of Thessaloniki（亚里士多德大学）；UC San Diego（加州大学圣迭戈分校）
In this paper, we introduce a novel suspect-and-investigate framework, which can be easily embedded in a drone for automated parking violation detection (PVD). Our proposed framework consists of: 1) SwiftFlow, an efficient and accurate convolutional neural network (CNN) for unsupervised optical flow estimation; 2) Flow-RCNN, a flow-guided CNN for car detection and classification; and 3) an illegally parked car (IPC) candidate investigation module developed based on visual SLAM. The proposed framework was successfully embedded in a drone from ATG Robotics. The experimental results demonstrate t…
KIOS Research and Innovation Center of Excellence（KIOS卓越研究与创新中心）；University of Cyprus（塞浦路斯大学）
Unmanned Aerial Vehicles (UAVs), equipped with camera sensors can facilitate enhanced situational awareness for many emergency response and disaster management applications since they are capable of operating in remote and difficult to access areas. In addition, by utilizing an embedded platform and deep learning UAVs can autonomously monitor a disaster stricken area, analyze the image in real-time and alert in the presence of various calamities such as collapsed buildings, flood, or fire in order to faster mitigate their effects on the environment and on human population. To this end, this pa…
In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification. Based on Associative Memories, this layer can help design Deep Neural Networks which support incremental learning and that can be (partially) trained in real time on embedded devices. Experiments on the ImageNet dataset and other different domain specific datasets show that it is possible to design more flexible and faster-to-train Neural Networks at the cost of a slight decrease in accuracy.
Steganography and digital watermarking are the tasks of hiding recoverable data in image pixels. Deep neural network (DNN) based image steganography and watermarking techniques are quickly replacing traditional hand-engineered pipelines. DNN based watermarking techniques have drastically improved the message capacity, imperceptibility and robustness of the embedded watermarks. However, this improvement comes at the cost of increased computational overhead of the watermark encoder neural network. In this work, we design the first accelerator platform FastStamp to perform DNN based steganography…
