High-speed Object Detection Research Articles

PENERAPAN YOLOV5 DAN SORT DALAM DETEKSI KENDARAAN PADA PERSIMPANGAN BERSINYAL UNTUK PENYESUAIAN WAKTU LAMPU LALU LINTAS

The problems with traffic in many big cities is congestion. Detection and tracking of vehicles in traffic light queues is an important aspect of an efficient urban transport system. This research introduces a combined model that combines the YOLO (You Only Look Once) version 5 algorithm or commonly called YOLOv5, a high-speed object detection approach, with the SORT (Simple Online and Realtime Tracking) algorithm to efficiently detect and track vehicles. The method was tested using a dataset of real traffic recordings and the results showed excellent performance in detecting and tracking vehicles, with sufficient accuracy and speed for urban traffic applications. Using this approach, vehicle detection and tracking systems can improve traffic safety and optimize vehicle flow at road intersections.

Drivable Road Region Segmentation in Real Time with High Precision using Deep Learning

Abstract: This paper presents a novel approach that addresses the challenging task of real-time drivable road region extraction in computer vision. Semantic segmentation, which involves accurately identifying and segmenting objects in real-time data, is a complex problem. However, deep learning has proven to be a powerful technique for achieving semantic segmentation by automatically identifying patterns without the need for explicit programming. To tackle this task, the paper proposes a fusion of the YOLO algorithm and UNET architecture, leveraging their respective strengths. The YOLO algorithm enables high-speed object detection, while the UNET architecture provides advantages in global location utilization, contextual understanding, and performance, even with limited training samples. Importantly, the proposed method is lightweight, making it suitable for deployment on embedded systems with limited computational power. To optimize memory usage and capture context at different scales, the system employs dilated convolutions for efficient feature extraction. The algorithm exhibits exceptional performance in accurately segmenting irregular objects and handles diverse input data types, including images and videos, in real-time. Overall, this paper contributes significantly to the advancement of computer vision technologies and offers a valuable solution for real-time drivable road region extraction. Its potential applications include addressing driving challenges and enhancing safety in autonomous vehicles and intelligent transportation systems.

1000× Faster Camera and Machine Vision with Ordinary Devices

In digital cameras, we find a major limitation: the image and video form inherited from a film camera obstructs it from capturing the rapidly changing photonic world. Here, we present vidar, a bit sequence array where each bit represents whether the accumulation of photons has reached a threshold, to record and reconstruct the scene radiance at any moment. By employing only consumer-level CMOS sensors and integrated circuits, we have developed a vidar camera that is 1,000x faster than conventional cameras. By treating vidar as spike trains in biological vision, we have further developed a spiking neural network-based machine vision system that combines the speed of the machine and the mechanism of biological vision, achieving high-speed object detection and tracking 1,000x faster than human vision. We demonstrate the utility of the vidar camera and the super vision system in an assistant referee and target pointing system. Our study is expected to fundamentally revolutionize the image and video concepts and related industries, including photography, movies, and visual media, and to unseal a new spiking neural network-enabled speed-free machine vision era.

High-speed object detection with a single-photon time-of-flight image sensor.

3D time-of-flight (ToF) imaging is used in a variety of applications such as augmented reality (AR), computer interfaces, robotics and autonomous systems. Single-photon avalanche diodes (SPADs) are one of the enabling technologies providing accurate depth data even over long ranges. By developing SPADs in array format with integrated processing combined with pulsed, flood-type illumination, high-speed 3D capture is possible. However, array sizes tend to be relatively small, limiting the lateral resolution of the resulting depth maps and, consequently, the information that can be extracted from the image for applications such as object detection. In this paper, we demonstrate that these limitations can be overcome through the use of convolutional neural networks (CNNs) for high-performance object detection. We present outdoor results from a portable SPAD camera system that outputs 16-bin photon timing histograms with 64×32 spatial resolution, with each histogram containing thousands of photons. The results, obtained with exposure times down to 2 ms (equivalent to 500 FPS) and in signal-to-background (SBR) ratios as low as 0.05, point to the advantages of providing the CNN with full histogram data rather than point clouds alone. Alternatively, a combination of point cloud and active intensity data may be used as input, for a similar level of performance. In either case, the GPU-accelerated processing time is less than 1 ms per frame, leading to an overall latency (image acquisition plus processing) in the millisecond range, making the results relevant for safety-critical computer vision applications which would benefit from faster than human reaction times.

Optimization and Implementation of Synthetic Basis Feature Descriptor on FPGA

Feature detection, description, and matching are crucial steps for many computer vision algorithms. These steps rely on feature descriptors to match image features across sets of images. Previous work has shown that our SYnthetic BAsis (SYBA) feature descriptor can offer superior performance to other binary descriptors. This paper focused on various optimizations and hardware implementation of the newer and optimized version. The hardware implementation on a field-programmable gate array (FPGA) is a high-throughput low-latency solution which is critical for applications such as high-speed object detection and tracking, stereo vision, visual odometry, structure from motion, and optical flow. We compared our solution to other hardware designs of binary descriptors. We demonstrated that our implementation of SYBA as a feature descriptor in hardware offered superior image feature matching performance and used fewer resources than most binary feature descriptor implementations.

Compressed Domain Image Classification Using a Dynamic-Rate Neural Network

Compressed domain image classification performs classification directly on compressive measurements acquired from the single-pixel camera, bypassing the image reconstruction step. It is of great importance for extending high-speed object detection and classification beyond the visible spectrum in a cost-effective manner especially for resource-limited platforms. Previous neural network methods require training a dedicated neural network for each different measurement rate (MR), which is costly in computation and storage. In this work, we develop an efficient training scheme that provides a neural network with dynamic-rate property, where a single neural network is capable of classifying over any MR within the range of interest with a given sensing matrix. This training scheme uses only a few selected MRs for training and the trained neural network is valid over the full range of MRs of interest. We demonstrate the performance of the dynamic-rate neural network on datasets of MNIST, CIFAR-10, Fashion-MNIST, COIL-100, and show that it generates approximately equal performance at each MR as that of a single-rate neural network valid only for one MR. Robustness to noise of the dynamic-rate model is also demonstrated. The dynamic-rate training scheme can be regarded as a general approach compatible with different types of sensing matrices, various neural network architectures, and is a valuable step towards wider adoption of compressive inference techniques and other compressive sensing related tasks via neural networks.

Algorithm to improve the efficiency of high-speed object detection

Algorithm to improve the efficiency of high-speed object detection

Compressive image acquisition and classification via secant projections

Given its importance in a wide variety of machine vision applications, extending high-speed object detection and recognition beyond the visible spectrum in a cost-effective manner presents a significant technological challenge. As a step in this direction, we developed a novel approach for target image classification using a compressive sensing architecture. Here we report the first implementation of this approach utilizing the compressive single-pixel camera system. The core of our approach rests on the design of new measurement patterns, or projections, that are tuned to objects of interest. Our measurement patterns are based on the notion of secant projections of image classes that are constructed using two different approaches. Both approaches show at least a twofold improvement in terms of the number of measurements over the conventional, data-oblivious compressive matched filter. As more noise is added to the image, the second method proves to be the most robust.

FPGA-Based Object Detection and Motion Tracking in Micro- and Nanorobotics

Object-detection and classification is a key task in micro- and nanohandling. The microscopic imaging is often the only available sensing technique to detect information about the positions and orientations of objects. FPGA-based image processing is superior to state of the art PC-based image processing in terms of achievable update rate, latency and jitter. A connected component labeling algorithm is presented and analyzed for its high speed object detection and classification feasibility. The features of connected components are discussed and analyzed for their feasibility with a single-pass connected component labeling approach, focused on principal component analysis-based features. It is shown that an FPGA implementation of the algorithm can be used for high-speed tool tracking as well as object classification inside optical microscopes. Furthermore, it is shown that an FPGA implementation of the algorithm can be used to detect and classify carbon-nanotubes (CNTs) during image acquisition in a scanning electron microscope, allowing fast object detection before the whole image is captured.