Review on Panoramic Imaging and Its Applications in Scene Understanding

  title={Review on Panoramic Imaging and Its Applications in Scene Understanding},
  author={Shaohua Gao and Kailun Yang and Haowen Shi and Kaiwei Wang and Jian Bai},
  journal={IEEE Transactions on Instrumentation and Measurement},
With the rapid development of high-speed communication and artificial intelligence technologies, human perception of real-world scenes is no longer limited to the use of small Field of View (FoV) and low-dimensional scene detection devices. Panoramic imaging emerges as the next generation of innovative intelligent instruments for environmental perception and measurement. However, while satisfying the need for large-FoV photographic imaging, panoramic imaging instruments are expected to have… 

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

—Panoramic Annular Lens (PAL) composed of few lenses has great potential in panoramic surrounding sensing tasks for mobile and wearable devices because of its tiny size and large Field of View (FoV).

PanoFlow: Learning 360{\deg} Optical Flow for Surrounding Temporal Understanding

This paper proposes a Cyclic Flow Estimation (CFE) method by leveraging the cyclicity of spherical images to infer 360 ◦ optical flow and converting large displacement to relatively small displacement and achieves state-of-the-art performance on the public OmniFlowNet and the fresh established Flow360 benchmarks.

Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning

This work proposes a framework which allows model training on standard pinhole images and transfers the learned features to a different domain in a cost-minimizing way, and experiment with different target models in order to prove the effectiveness of the proposed approach and to identify models which are most suitable for panoramic panoptic segmentation.

Attitude-Guided Loop Closure for Cameras with Negative Plane

This work proposes a loop closure framework with a new outlier rejection method based on the unit length representation, to improve the accuracy of LF-VIO and outperforms state-of-the-art visual-inertial-odometry methods.

Computational Optics Meet Domain Adaptation: Transferring Semantic Segmentation Beyond Aberrations

This paper investigates Semantic Segmentation under Optical Aberrations (SSOA) of MOS through an unsupervised domain adaptation perspective, and proposes Computational Imaging Assisted Domain Adaptation (CIADA) to leverage prior knowledge of CI for robust performance in SSOA.

SLAM Overview: From Single Sensor to Heterogeneous Fusion

It is predicted that SLAM technology combining LIDAR and visual sensors, as well as various other sensors, will be the mainstream direction in the future.

Survey on Fish-Eye Cameras and Their Applications in Intelligent Vehicles

This work introduces the projection principle of fish-eye cameras, and four classic fish- Eye image representation models are presented, and the typical fish- eye datasets are present, including real collected data and virtually generated data.

FlowLens: Seeing Beyond the FoV via Flow-guided Clip-Recurrent Transformer

This paper proposes a novel task, aiming to exploit past visual cues and bidirectional break through the physical FoV of a camera, and proposes a FlowLens architecture to expand the FoV by achieving feature propagation explicitly by optical and implicitly by a novel clip-recurrent transformer.

Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation

This paper addresses panoramic semantic segmentation, which provides a full-view and dense-pixel understanding of surroundings in a holistic way and introduces the upgraded Trans4PASS+ model, featuring DMLPv2 with parallel token mixing to improve the flexibility and generalizability in modeling discriminative cues.



Panomoprh Based Panoramic Vision Sensors

This chapter presents the most recent advances in the panomorph vision sensor from the sky lens to the multi-task cameras.

A Cylindrical Virtual Space Based Catadioptric Real-time Panorama Imaging System

A new method to construct cylindrical image-based virtual space (IBVS) automatically with smooth quadric convex curved mirror catadioptric imaging is proposed, and the projection transformation with conic reflection surface and telecentric lens is described in detail.

Panoramic lens applications revisited

During the last few years, innovative optical design strategies to generate and control image mapping have been successful in producing high-resolution digital imagers and projectors. This new

Acquisition of omnidirectional stereoscopic images and videos of dynamic scenes: a review

A comparative study of the different cameras and methods to create stereoscopic panoramas of a scene, highlighting those that can be used for the real-time acquisition of imagery and video, is presented.

Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes

This research extends PADENet, which first appeared in previous conference work for outdoor scene understanding, to perform panoramic monocular depth estimation with a focus for indoor scenes, and improves the training process of the neural network adapted to the characteristics ofpanoramic images.

Panoramic imaging - a review

Panoramic thermal imaging: challenges and tradeoffs

Over the past decade, we have witnessed a growing demand for electro-optical systems that can provide continuous 3600 coverage. Applications such as perimeter security, autonomous vehicles, and

High-performance panoramic annular lens design for real-time semantic segmentation on aerial imagery

This work designs an efficient deep architecture for aerial scene segmentation that has higher recognition accuracy with the mean IoU greater than 86.30%, which provides an important reference for the drone system to monitor and identify specific targets in real-time in a large FoV.

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

—Panoramic Annular Lens (PAL) composed of few lenses has great potential in panoramic surrounding sensing tasks for mobile and wearable devices because of its tiny size and large Field of View (FoV).

Design of a novel panoramic lens without central blindness

A novel panoramic system consisting of two optical channels to overcome blind area in the center field of vision, the system has a field of view (FOV) reaching 200 in vertical and 360 in horizontal direction without blindness area, providing design flexibility to meet application requirements where the center FOV or the marginal FOV is of more interest.