Hybrid field of view vision: From biological inspirations to integrated sensor design

Rostkowska, Marta; Skrzypczyński, Piotr

doi:10.1109/mfi.2016.7849557

Cited by 4 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No significant difference was noticed between the results obtained for omnidirectional and panoramic images, which indicates that for appearance-based localization with our approach, it is unnecessary to convert the omnidirectional images to panoramic images. Hence, we can avoid the time-consuming conversion and rectification procedure [ 8 ], without compromising the results.…”

Section: Resultsmentioning

confidence: 99%

“…No significant difference was noticed between the results obtained for omnidirectional and panoramic images, which indicates that for appearancebased localization with our approach, it is unnecessary to convert the omnidirectional images to panoramic images. Hence, we can avoid the time-consuming conversion and rectification procedure [8], without compromising the results. As a follow-up of Experiment 2, a comparison of localization results was performed between the NetVLAD approach with VGG-16 and VLAD layer, and our approach with two variants of the EfficientNet backbone.…”

Section: Methodsmentioning

confidence: 99%

“…The catadioptric camera in this sensor consists of a Microsoft LifeCam and a hyperbolic mirror, which provides a field of view of 360 • and produces images with a resolution of 640 × 480. The images are processed by a Nvidia Jetson TX2 computer integrated with the sensor [8] The Jetson TX2 offers a 256-core Pascal architecture General Purpose Graphics Processing Unit (GPGPU) to support the real-time operation of the localization system. The considered dataset contains 606 images (Figure 4a,b), which were recorded on three floors of the Pozna ń University of Technology Mechatronics Centre building (Figure 3b).…”

Section: Experiments 1: Integrated Sensor On a Mobile Robotmentioning

confidence: 99%

“…Therefore, we propose a solution to the problem of global localization in a known (entirely or partially) environment using a passive catadioptric camera and the principle of recognizing places previously visited by the robot ( Figure 1 ). The applied sensor with a catadioptric camera is a variant of the biologically inspired sensor with a hybrid field of view that we introduced in [ 8 ]. This sensor uses a catadioptric camera to achieve omnidirectional vision, an analogue of the peripheral vision found in vertebrates [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

“…It allows animals to orient themselves to changes and hazards in the environment quickly. The sensor described in [ 8 , 9 ] is complemented by a moving perspective camera that performs the functions of foveal vision, the more accurate but spatially limited vision mode in animals. This function is not used in the research presented in this article, as we limit the scope to global appearance-based localization, i.e., the assignment of the robot’s current location to one of the previously recognized (visited) places.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Optimizing Appearance-Based Localization with Catadioptric Cameras: Small-Footprint Models for Real-Time Inference on Edge Devices

Rostkowska

Skrzypczyński

2023

Sensors

Self Cite

View full text Add to dashboard Cite

This paper considers the task of appearance-based localization: visual place recognition from omnidirectional images obtained from catadioptric cameras. The focus is on designing an efficient neural network architecture that accurately and reliably recognizes indoor scenes on distorted images from a catadioptric camera, even in self-similar environments with few discernible features. As the target application is the global localization of a low-cost service mobile robot, the proposed solutions are optimized toward being small-footprint models that provide real-time inference on edge devices, such as Nvidia Jetson. We compare several design choices for the neural network-based architecture of the localization system and then demonstrate that the best results are achieved with embeddings (global descriptors) yielded by exploiting transfer learning and fine tuning on a limited number of catadioptric images. We test our solutions on two small-scale datasets collected using different catadioptric cameras in the same office building. Next, we compare the performance of our system to state-of-the-art visual place recognition systems on the publicly available COLD Freiburg and Saarbrücken datasets that contain images collected under different lighting conditions. Our system compares favourably to the competitors both in terms of the accuracy of place recognition and the inference time, providing a cost- and energy-efficient means of appearance-based localization for an indoor service robot.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Experiments 1: Integrated Sensor On a Mobile Robotmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations