Search results for "Object Detection"
showing 10 items of 64 documents
Temperate Fish Detection and Classification: a Deep Learning based Approach
2021
A wide range of applications in marine ecology extensively uses underwater cameras. Still, to efficiently process the vast amount of data generated, we need to develop tools that can automatically detect and recognize species captured on film. Classifying fish species from videos and images in natural environments can be challenging because of noise and variation in illumination and the surrounding habitat. In this paper, we propose a two-step deep learning approach for the detection and classification of temperate fishes without pre-filtering. The first step is to detect each single fish in an image, independent of species and sex. For this purpose, we employ the You Only Look Once (YOLO) …
An adaptive multi-rate system for visual tracking in augmented reality applications
2016
The visual tracking of an object is a well-known problem, and it involves many fields of applications. Often a single sensor, the camera, could not provide enough information in order to track the whole object trajectory due to a low updating rate; therefore a multi-sensor system, based also on inertial measurements, could be necessary to improve the tracking accuracy. This leads to the fundamental question: how can information from different sensors be combined when they work at different rates? In this paper an approach based on recursive parameter estimation focusing on multi-rate situations is suggested. The problem is here formulated as the state-of-the-art problem of the visual tracki…
Scratches Removal in Digitised Aerial Photos Concerning Sicilian Territory
2007
In this paper we propose a fast and effective method to detect and restore scratches in aerial photos from a photographic archive concerning Sicilian territory. Scratch removal is a typical problem for old movie films but similar defects can be seen in still images. Our solution is based on a semiautomatic detection process and an unsupervised restoration algorithm. Results are comparable with those obtained with commercial restoration tools.
Automated detection and classification of synoptic scale fronts from atmospheric data grids
2021
<p>Automatic determination of fronts from atmospheric data is an important task for weather prediction as well as for research of synoptic scale phenomena. We developed a deep neural network to detect and classify fronts from multi-level ERA5 reanalysis data. Model training and prediction is evaluated using two different regions covering Europe and North America with data from two weather services. Due to a label deformation step performed during training we are able to directly generate frontal lines with no further thinning during post processing. Our network compares well against the weather service labels with a Critical Success Index higher than 66.9% and a Object Detecti…
Logo detection in images using HOG and SIFT
2017
In this paper we present a study of logo detection in images from a media agency. We compare two most widely used methods — HOG and SIFT on a challenging dataset of images arising from a printed press and news portals. Despite common opinion that SIFT method is superior, our results show that HOG method performs significantly better on our dataset. We augment the HOG method with image resizing and rotation to improve its performance even more. We found out that by using such approach it is possible to obtain good results with increased recall and reasonably decreased precision.
Video preprocessing for audiovisual indexing
2003
We address the problem of detecting shots of subjects that are interviewed in news sequences. This is useful since usually these kinds of scenes contain important and reusable information that can be used for other news programs. In a previous paper, we presented a technique based on a priori knowledge of the editing techniques used in news sequences which allowed a fast search of news stories (see Albiol, A. et al., 3rd Int. Conf. on Audio and Video-based Biometric Person Authentication, p.366-71, 2001). We now present a new shot descriptor technique which improves the previous search results by using a simple, yet efficient, algorithm, based on the information contained in consecutive fra…
Real Time Robust Embedded Face Detection Using High Level Description
2011
Face detection is a fundamental prerequisite step in the process of face recognition. It consists of automatically finding all the faces in an image despite the considerable variations of lighting, background, appearance of people, position/orientation of faces, and their sizes. This type of object detection has the distinction of having a very large intra-class, making it a particularly difficult problem to solve, especially when one wishes to achieve real time processing. A human being has a great ability to analyze images. He can extract the information about it and focus only on areas of interest (the phenomenon of attention). Thereafter he can detect faces in an extremely reliable way.…
DenseYOLO: Yet Faster, Lighter and More Accurate YOLO
2020
As much as an object detector should be accurate, it should be light and fast as well. However, current object detectors tend to be either inaccurate when lightweight or very slow and heavy when accurate. Accordingly, determining tolerable tradeoff between speed and accuracy of an object detector is not a simple task. One of the object detectors that have commendable balance of speed and accuracy is YOLOv2. YOLOv2 performs detection by dividing an input image into grids and training each grid cell to predict certain number of objects. In this paper we propose a new approach to even make YOLOv2 more fast and accurate. We re-purpose YOLOv2 into a dense object detector by using fine-grained gr…
Online Multi-Person Tracking by Tracker Hierarchy
2012
Tracking-by-detection is a widely used paradigm for multi-person tracking but is affected by variations in crowd density, obstacles in the scene, varying illumination, human pose variation, scale changes, etc. We propose an improved tracking-by-detection framework for multi-person tracking where the appearance model is formulated as a template ensemble updated online given detections provided by a pedestrian detector. We employ a hierarchy of trackers to select the most effective tracking strategy and an algorithm to adapt the conditions for trackers' initialization and termination. Our formulation is online and does not require calibration information. In experiments with four pedestrian t…
Deep Learning-Based Real-Time Object Detection in Inland Navigation
2019
International audience; Semi-autonomous and fully-autonomous systems must have knowledge about the objects in their environment to ensure a safe navigation. Modern approaches implement deep learning techniques to train a neural network for object detection. This project will study the effectiveness of using several promising algorithms such as Faster R-CNN, SSD, and different versions of YOLO, to detect, classify, and track objects in near real-time fluvial domain. Since no dataset is available for this purpose in literature, we first started by annotating a dataset of 2488 images with almost 35 400 annotations for training the convolutional neural network architectures. We made this data s…