Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in people's life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning algorithms for detection tasks, the performance of object detectors has been greatly improved. In order to understand the main development status of object detection pipeline thoroughly and deeply, in this survey, we analyze the methods of existing typical detection models and describe the benchmark datasets at first. Afterwards and primarily, we provide a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors. Moreover, we list the traditional and new applications. Some representative branches of object detection are analyzed as well. Finally, we discuss the architecture of exploiting these object detection methods to build an effective and efficient system and point out a set of development trends to better follow the state-of-the-art algorithms and further research.

A Survey of Deep Learning-Based Object Detection

The last decade has witnessed a growing interest in video salient object detection (VSOD). However, the research community long-term lacked a well-established VSOD dataset representative of real dynamic scenes with high-quality annotations. To address this issue, we elaborately collected a visual-attention-consistent Densely Annotated VSOD (DAVSOD) dataset, which contains 226 videos with 23,938 frames that cover diverse realistic-scenes, objects, instances and motions. With corresponding real human eye-fixation data, we obtain precise ground-truths. This is the first work that explicitly emphasizes the challenge of saliency shift, i.e., the video salient object(s) may dynamically change. To further contribute the community a complete benchmark, we systematically assess 17 representative VSOD algorithms over seven existing VSOD datasets and our DAVSOD with totally ~84K frames (largest-scale). Utilizing three famous metrics, we then present a comprehensive and insightful performance analysis. Furthermore, we propose a baseline model. It is equipped with a saliency shift- aware convLSTM, which can efficiently capture video saliency dynamics through learning human attention-shift behavior. Extensive experiments open up promising future directions for model development and comparison.

/pdf/shifting-more-attention-to-video-salient-object-detection-4vtwyjb99t.pdf

Shifting More Attention to Video Salient Object Detection

The ability to present three-dimensional (3D) scenes with continuous depth sensation has a profound impact on virtual and augmented reality, human–computer interaction, education and training. Computer-generated holography (CGH) enables high-spatio-angular-resolution 3D projection via numerical simulation of diffraction and interference1. Yet, existing physically based methods fail to produce holograms with both per-pixel focal control and accurate occlusion2,3. The computationally taxing Fresnel diffraction simulation further places an explicit trade-off between image quality and runtime, making dynamic holography impractical4. Here we demonstrate a deep-learning-based CGH pipeline capable of synthesizing a photorealistic colour 3D hologram from a single RGB-depth image in real time. Our convolutional neural network (CNN) is extremely memory efficient (below 620 kilobytes) and runs at 60 hertz for a resolution of 1,920 × 1,080 pixels on a single consumer-grade graphics processing unit. Leveraging low-power on-device artificial intelligence acceleration chips, our CNN also runs interactively on mobile (iPhone 11 Pro at 1.1 hertz) and edge (Google Edge TPU at 2.0 hertz) devices, promising real-time performance in future-generation virtual and augmented-reality mobile headsets. We enable this pipeline by introducing a large-scale CGH dataset (MIT-CGH-4K) with 4,000 pairs of RGB-depth images and corresponding 3D holograms. Our CNN is trained with differentiable wave-based loss functions5 and physically approximates Fresnel diffraction. With an anti-aliasing phase-only encoding method, we experimentally demonstrate speckle-free, natural-looking, high-resolution 3D holograms. Our learning-based approach and the Fresnel hologram dataset will help to unlock the full potential of holography and enable applications in metasurface design6,7, optical and acoustic tweezer-based microscopic manipulation8–10, holographic microscopy11 and single-exposure volumetric 3D printing12,13. A deep-learning-based approach using a convolutional neural network is used to synthesize photorealistic colour three-dimensional holograms from a single RGB-depth image in real time, and termed tensor holography.

Towards real-time photorealistic 3D holography with deep neural networks

In recent years, attention models have been extensively used for person and vehicle re-identification. Most re-identification methods are designed to focus attention on key-point locations. However, depending on the orientation, the contribution of each key-point varies. In this paper, we present a novel dual-path adaptive attention model for vehicle re-identification (AAVER). The global appearance path captures macroscopic vehicle features while the orientation conditioned part appearance path learns to capture localized discriminative features by focusing attention on the most informative key-points. Through extensive experimentation, we show that the proposed AAVER method is able to accurately re-identify vehicles in unconstrained scenarios, yielding state of the art results on the challenging dataset VeRi-776. As a byproduct, the proposed system is also able to accurately predict vehicle key-points and shows an improvement of more than 7% over state of the art. The code for key-point estimation model is available at https://github.com/Pirazh/Vehicle_Key_ Point_Orientation_Estimation

/pdf/a-dual-path-model-with-adaptive-attention-for-vehicle-re-jbfy91pqtv.pdf

A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification

A survey of advances in vision-based vehicle re-identification

This paper presents a novel model for video salient object detection called spatiotemporal constrained optimization model (SCOM), which exploits spatial and temporal cues, as well as a local constraint, to achieve a global saliency optimization. For a robust motion estimation of salient objects, we propose a novel approach to modeling the motion cues from optical flow field, the saliency map of the prior video frame and the motion history of change detection, which is able to distinguish the moving salient objects from diverse changing background regions. Furthermore, an effective objectness measure is proposed with intuitive geometrical interpretation to extract some reliable object and background regions, which provided as the basis to define the foreground potential, background potential, and the constraint to support saliency propagation. These potentials and the constraint are formulated into the proposed SCOM framework to generate an optimal saliency map for each frame in a video. The proposed model is extensively evaluated on the widely used challenging benchmark data sets. Experiments demonstrate that our proposed SCOM substantially outperforms the state-of-the-art saliency models.

SCOM: Spatiotemporal Constrained Optimization for Salient Object Detection

It is a critical issue to reduce the enormous amount of data in the processing, storage and transmission of a hologram in digital format. In photograph compression, the JPEG standard is commonly supported by almost every system and device. It will be favorable if JPEG standard is applicable to hologram compression, with advantages of universal compatibility. However, the reconstructed image from a JPEG compressed hologram suffers from severe quality degradation since some high frequency features in the hologram will be lost during the compression process. In this work, we employ a deep convolutional neural network to reduce the artifacts in a JPEG compressed hologram. Simulation and experimental results reveal that our proposed “JPEG + deep learning” hologram compression scheme can achieve satisfactory reconstruction results for a computer-generated phase-only hologram after compression.

Compression of Phase-Only Holograms with JPEG Standard and Deep Learning

Vehicle re-identification (Re-Id) aims to retrieve the same vehicle captured by disjoint cameras at different time instants from different locations, and is a challenging task mainly due to the high similarity among the captured vehicle images in surveillance environment. With the rapid development of Convolutional Neural Network (CNN), learning-based deep features have been adopted to combine with hand-crafted features to re-identify vehicles in traffic surveillance environment. However, the two kinds of features are in different feature space, and if they are fused directly together, their complementary correlation is not able to be fully explored. To address such an issue, this paper proposes a multi-modal metric learning architecture to fuse deep features and hand-crafted ones in an end-to-end optimization network, which achieves a more robust and discriminative feature representation for vehicle re-identification. The extensive experiments on a large-scale traffic surveillance vehicle dataset demonstrate that our proposed approach substantially outperforms the state-of-the-art methods on vehicle Re-Id.

Multi-modal metric learning for vehicle re-identification in traffic surveillance environment

Quick response (QR) code has been employed as a data carrier for optical cryptosystems in many recent research works, and the error-correction coding mechanism allows the decrypted result to be noise free. However, in this paper, we point out for the first time that the Reed-Solomon coding algorithm in QR code is not a very suitable option for the nonlocally distributed speckle noise in optical cryptosystems from an information coding perspective. The average channel capacity is proposed to measure the data storage capacity and noise-resistant capability of different encoding schemes. We design an alternative 2D barcode scheme based on Bose–Chaudhuri–Hocquenghem (BCH) coding, which demonstrates substantially better average channel capacity than QR code in numerical simulated optical cryptosystems.

Is QR code an optimal data container in optical encryption systems from an error-correction coding perspective?

In this paper, a special ciphertext-only attack (COA) scenario to the traditional double random phase encoding (DRPE) technique is proposed based on plaintext shifting. We assume the attacker can illegally manipulate the DRPE system to gain multiple ciphertexts from randomly shifted versions of the same plaintext. The plaintext image can be recovered when our proposed scenario is combined with a speckle correlation attacking method proposed in previous work. Simulation results demonstrate that our proposed scheme can successfully crack the DRPE system even when the speckle correlation method alone fails to work in the conventional single ciphertext scenario due to the small size of the plaintext image. The work in this paper reveals a severe security flaw of DRPE systems when minor position shifting of the plaintext occurs.

Xia Li

Papers

SCOM: Spatiotemporal Constrained Optimization for Salient Object Detection

Compression of Phase-Only Holograms with JPEG Standard and Deep Learning

Multi-modal metric learning for vehicle re-identification in traffic surveillance environment

Is QR code an optimal data container in optical encryption systems from an error-correction coding perspective?

Special ciphertext-only attack to double random phase encryption by plaintext shifting with speckle correlation