arXiv subjects

Jiaming Zhang

Publications and source records attributed to Jiaming Zhang.

192 records · Page 11Linked to original sources

arXiv2021

Pose2Drone: A Skeleton-Pose-based Framework for Human-Drone Interaction

Drones have become a common tool, which is utilized in many tasks such as aerial photography, surveillance, and delivery. However, operating a drone requires more and more interaction with the user. A natural and safe method for Human-Drone Interaction (HDI) is using gestures. In this paper, we introduce an HDI framework building upon skeleton-based pose estimation. Our framework provides the functionality to control the movement of the drone with simple arm gestures and to follow the user while keeping a safe distance. We also propose a monocular distance estimation method, which is entirely based on image features and does not require any additional depth sensors. To perform comprehensive experiments and quantitative analysis, we create a customized testing dataset. The experiments indicate that our HDI framework can achieve an average of 93.5\% accuracy in the recognition of 11 common gestures. The code is available at: https://github.com/Zrrr1997/Pose2Drone

cs.CV↗

arXiv2021

Learning a Skill-sequence-dependent Policy for Long-horizon Manipulation Tasks

In recent years, the robotics community has made substantial progress in robotic manipulation using deep reinforcement learning (RL). Effectively learning of long-horizon tasks remains a challenging topic. Typical RL-based methods approximate long-horizon tasks as Markov decision processes and only consider current observation (images or other sensor information) as input state. However, such approximation ignores the fact that skill-sequence also plays a crucial role in long-horizon tasks. In this paper, we take both the observation and skill sequences into account and propose a skill-sequence-dependent hierarchical policy for solving a typical long-horizon task. The proposed policy consists of a high-level skill policy (utilizing skill sequences) and a low-level parameter policy (responding to observation) with corresponding training methods, which makes the learning much more sample-efficient. Experiments in simulation demonstrate that our approach successfully solves a long-horizon task and is significantly faster than Proximal Policy Optimization (PPO) and the task schema methods.

cs.RO↗

arXiv2021

Capturing Omni-Range Context for Omnidirectional Segmentation

Convolutional Networks (ConvNets) excel at semantic segmentation and have become a vital component for perception in autonomous driving. Enabling an all-encompassing view of street-scenes, omnidirectional cameras present themselves as a perfect fit in such systems. Most segmentation models for parsing urban environments operate on common, narrow Field of View (FoV) images. Transferring these models from the domain they were designed for to 360-degree perception, their performance drops dramatically, e.g., by an absolute 30.0% (mIoU) on established test-beds. To bridge the gap in terms of FoV and structural distribution between the imaging domains, we introduce Efficient Concurrent Attention Networks (ECANets), directly capturing the inherent long-range dependencies in omnidirectional imagery. In addition to the learned attention-based contextual priors that can stretch across 360-degree images, we upgrade model training by leveraging multi-source and omni-supervised learning, taking advantage of both: Densely labeled and unlabeled data originating from multiple datasets. To foster progress in panoramic image segmentation, we put forward and extensively evaluate models on Wild PAnoramic Semantic Segmentation (WildPASS), a dataset designed to capture diverse scenes from all around the globe. Our novel model, training regimen and multi-source prediction fusion elevate the performance (mIoU) to new state-of-the-art results on the public PASS (60.2%) and the fresh WildPASS (69.0%) benchmarks.

cs.CV↗

arXiv2021

Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impaired

Classic computer vision algorithms, instance segmentation, and semantic segmentation can not provide a holistic understanding of the surroundings for the visually impaired. In this paper, we utilize panoptic segmentation to assist the navigation of visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired efficiently. To this end, we propose an efficient Attention module -- Lintention which can model long-range interactions in linear time using linear space. Based on Lintention, we then devise a novel panoptic segmentation model which we term Panoptic Lintention Net. Experiments on the COCO dataset indicate that the Panoptic Lintention Net raises the Panoptic Quality (PQ) from 39.39 to 41.42 with 4.6\% performance gain while only requiring 10\% fewer GFLOPs and 25\% fewer parameters in the semantic branch. Furthermore, a real-world test via our designed compact wearable panoptic segmentation system, indicates that our system based on the Panoptic Lintention Net accomplishes a relatively stable and exceptionally remarkable panoptic segmentation in real-world scenes.

cs.CV↗

arXiv2021

Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired

As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks. Building on the compact ResNet backbone, our designed network architecture has two paths with shared parameters. In the structure, the semantic segmentation path integrates fast attention, with the aim of harvesting long-range contextual information in an efficient manner. Simultaneously, the scene recognition path attains the scene type inference by passing the semantic features into semantic-driven attention networks and combining the semantic extracted representations with the RGB extracted representations through a gated attention module. In the experiments, we have verified the systems' accuracy and efficiency on both public datasets and real-world scenes. This system runs on a wearable belt with an Intel RealSense LiDAR camera and an Nvidia Jetson AGX Xavier processor, which can accompany visually impaired people and provide assistive scene information in their navigation tasks.

cs.CV↗

arXiv2020

Adversarial Privacy-preserving Filter

While widely adopted in practical applications, face recognition has been critically discussed regarding the malicious use of face images and the potential privacy problems, e.g., deceiving payment system and causing personal sabotage. Online photo sharing services unintentionally act as the main repository for malicious crawler and face recognition applications. This work aims to develop a privacy-preserving solution, called Adversarial Privacy-preserving Filter (APF), to protect the online shared face images from being maliciously used.We propose an end-cloud collaborated adversarial attack solution to satisfy requirements of privacy, utility and nonaccessibility. Specifically, the solutions consist of three modules: (1) image-specific gradient generation, to extract image-specific gradient in the user end with a compressed probe model; (2) adversarial gradient transfer, to fine-tune the image-specific gradient in the server cloud; and (3) universal adversarial perturbation enhancement, to append image-independent perturbation to derive the final adversarial noise. Extensive experiments on three datasets validate the effectiveness and efficiency of the proposed solution. A prototype application is also released for further evaluation.We hope the end-cloud collaborated attack framework could shed light on addressing the issue of online multimedia sharing privacy-preserving issues from user side.

cs.CR↗

arXiv2020

Can we cover navigational perception needs of the visually impaired by panoptic segmentation?

Navigational perception for visually impaired people has been substantially promoted by both classic and deep learning based segmentation methods. In classic visual recognition methods, the segmentation models are mostly object-dependent, which means a specific algorithm has to be devised for the object of interest. In contrast, deep learning based models such as instance segmentation and semantic segmentation allow to individually recognize part of the entire scene, namely things or stuff, for blind individuals. However, both of them can not provide a holistic understanding of the surroundings for the visually impaired. Panoptic segmentation is a newly proposed visual model with the aim of unifying semantic segmentation and instance segmentation. Motivated by that, we propose to utilize panoptic segmentation as an approach to navigating visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired. We demonstrate that panoptic segmentation is able to equip the visually impaired with a holistic real-world scene perception through a wearable assistive system.

cs.CV↗

arXiv2020

Optical System Design of Bionic Compound Eye with Broad Field of View

In nature, many common insects have compound eyes composed of many small eyes arranged on a curved retina. This kind of vision systems have many advantages, such as small size, large FOV (field of view) and high sensitivity, which have attracted extensive attention and research from world-wide researchers. It has good application prospects in military strikes and mechanical vision. In this paper, a new type of miniature compound eye system with large FOV is designed, which contains a micro-lens array and a relay system. Hexagonal micro-lens array are spliced seamlessly as a curved shell in the designed compound eye system. The intermediate curved image formed by the curved array is converted to a planar image by introducing a relay system. After combination and optimization of the micro-lens array and the relay system, the MTF values at 89.3lp/mm for each FOV within 120.5° are greater than 0.3, and the corresponding RMS spot radii less than the radius of the Airy disk, which proves the good imaging quality for the compound eye. The clear aperture of a single micro lens is 250μm with FOV 6°. After tolerance analysis, the results show the image quality still holds good enough performance and meets the requirements of the additive manufacturing process.

physics.optics↗

arXiv2019

blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Turing test was originally proposed to examine whether machine's behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognition-alike questions. The recent development of deep learning has significantly advanced the capability of algorithm in solving CAPTCHA questions, forcing CAPTCHA designers to increase question complexity. Instead of designing questions difficult for both algorithm and human, this study attempts to employ the limitations of algorithm to design robust CAPTCHA questions easily solvable to human. Specifically, our data analysis observes that human and algorithm demonstrates different vulnerability to visual distortions: adversarial perturbation is significantly annoying to algorithm yet friendly to human. We are motivated to employ adversarially perturbed images for robust CAPTCHA design in the context of character-based questions. Three modules of multi-target attack, ensemble adversarial training, and image preprocessing differentiable approximation are proposed to address the characteristics of character-based CAPTCHA cracking. Qualitative and quantitative experimental results demonstrate the effectiveness of the proposed solution. We hope this study can lead to the discussions around adversarial attack/defense in CAPTCHA design and also inspire the future attempts in employing algorithm limitation for practical usage.

cs.CV↗

arXiv2018

Multiple-parameter bifurcation analysis in a Kuramoto model with time delay and distributed shear

In this paper, time delay effect and distributed shear are considered in the Kuramoto model. On the Ott-Antonsen's manifold, through analyzing the associated characteristic equation of the reduced functional differential equation, the stability boundary of the incoherent state is derived in multiple-parameter space. Moreover, very rich dynamical behavior such as stability switches inducing synchronization switches can occur in this equation. With the loss of stability, Hopf bifurcating coherent states arise, and the criticality of Hopf bifurcations is determined by applying the normal form theory and the center manifold theorem. On one hand, theoretical analysis indicates that the width of shear distribution and time delay can both eliminate the synchronization then lead the Kuramoto model to incoherence. On the other, time delay can induce several coexisting coherent states. Finally, some numerical simulations are given to support the obtained results where several bifurcation diagrams are drawn, and the effect of time delay and shear is discussed.

nlin.CD↗

arXiv2012

Growth process and crystallographic properties of ammonia-induced vaterite

Metastable vaterite crystals were synthesized by increasing the pH and consequently the saturation states of Ca and CO3 containing solutions using an ammonia diffusion method. SEM and TEM analyses indicate that vaterite grains produced by this method are polycrystalline aggregates with a final morphology that has a sixfold-symmetry. The primary structure develops within an hour and is almost a spherical assemblage of nanoparticles (5 to 10 nm) with random orientation, followed by the formation of hexagonal platelets (1 to 2um), which are first composed of nanoparticles and that develop further into single crystals. As determined using transmission electron microscopy, these hexagonal crystallites are terminated by (001) surfaces and are bounded by 110 edges. The hexagonal crystals subsequently stack to form the petals (20um wide, 1um thick) of the final flower-like vaterite morphology. The large flakes gradually tilt toward the center as growth progresses so that their positions become more and more vertical, which eventually leads to a depression in the center. Since this sequence encompasses several morphologies observed in previous studies (spheres, hexagons, flowers etc), they may actually represent different stages of growth rather than equilibrium morphologies for specific growth conditions

cond-mat.mtrl-sci↗

arXiv2007

Electronic and Structural Characteristics of Zinc-Blende Wurtzite Biphasic Homostructure GaN Nanowires

We report a new biphasic crystalline wurtzite/zinc-blende homostructure in gallium nitride nanowires. Cathodoluminescence was used to quantitatively measure the wurtzite and zinc-blende band gaps. High resolution transmission electron microscopy was used to identify distinct wurtzite and zinc-blende crystalline phases within single nanowires through the use of selected area electron diffraction, electron dispersive spectroscopy, electron energy loss spectroscopy, and fast Fourier transform techniques. A mechanism for growth is identified.

cond-mat.mtrl-sci↗