Abstract

The 2WIDE_SENSE (WIDE spectral band & WIDE dynamics multifunctional imaging SENSor Enabling safer car transportation) EU funded project is aimed at the development of a low-cost camera sensor for Advanced Driver Assistance Systems (ADAS) applications able to acquire the full visible to Short Wave InfraRed (SWIR) spectrum from 400 to 1700 nm. This paper presents the first results obtained by investigating the SWIR contribution to pedestrian detection in difficult visibility conditions as haze and fog employing the wide-bandwidth camera developed within the project. Document type: Part of book or chapter of book

Abstract

This paper describes a system for pedestrian detection in infrared images implemented and tested on an experimental vehicle. A specific stabilization procedure is applied after image acquisition and before processing to cope with vehicle movements affecting the camera calibration. The localization of pedestrians is based on the search for warm symmetrical objects with specific size and aspect ratio. A set of filters is used to reduce false detections. The final validation process relies on the human shape’s morphological characteristics. Document type: Part of book or chapter of book

Abstract

Automatic multi-class object detection in remote sensing images in unconstrained scenarios is of high interest for several applications including traffic monitoring and disaster management. The huge variation in object scale, orientation, category, and complex backgrounds, as well as the different camera sensors pose great challenges for current algorithms. In this work, we propose a new method consisting of a novel joint image cascade and feature pyramid network with multi-size convolution kernels to extract multi-scale strong and weak semantic features. These features are fed into rotation-based region proposal and region of interest networks to produce object detections. Finally, rotational non-maximum suppression is applied to remove redundant detections. During training, we minimize joint horizontal and oriented bounding box loss functions, as well as a novel loss that enforces oriented boxes to be rectangular. Our method achieves 68.16% mAP on horizontal and 72.45% mAP on oriented bounding box detection tasks on the challenging DOTA dataset, outperforming all published methods by a large margin (+6% and +12% absolute improvement, respectively). Furthermore, it generalizes to two other datasets, NWPU VHR-10 and UCAS-AOD, and achieves competitive results with the baselines even when trained on DOTA. Our method can be deployed in multi-class object detection applications, regardless of the image and object scales and orientations, making it a great choice for unconstrained aerial and satellite imagery. Document type: Part of book or chapter of book