| 1. |
- Ahrnbom, Martin, et al.
(författare)
-
Fast Classification of Empty and Occupied Parking Spaces Using Integral Channel Features
- 2016
-
Ingår i: Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. - 9781467388504 ; , s. 1609-1615
-
Konferensbidrag (refereegranskat)abstract
- In this paper we present a novel, fast and accurate system for detecting the presence of cars in parking lots. The system is based on fast integral channel features and machine learning. The methods are well suited for running embedded on low performance platforms. The methods are tested on a database of nearly 700,000 images of parking spaces, where 48.5% are occupied and the rest are free. The experimental evaluation shows improved robustness in comparison to the baseline methods for the dataset.
|
|
| 2. |
- Ahrnbom, Martin, et al.
(författare)
-
Improving a real-time object detector with compact temporal information
- 2018
-
Ingår i: International Conference on Computer Vision Workshops, 2017 : Computer Vision for Road Scene Understanding and Autonomous Driving Workshop - Computer Vision for Road Scene Understanding and Autonomous Driving Workshop. ; , s. 190-197
-
Konferensbidrag (refereegranskat)abstract
- Neural networks designed for real-time object detectionhave recently improved significantly, but in practice, look-ing at only a single RGB image at the time may not be ideal.For example, when detecting objects in videos, a foregrounddetection algorithm can be used to obtain compact temporaldata, which can be fed into a neural network alongside RGBimages. We propose an approach for doing this, based onan existing object detector, that re-uses pretrained weightsfor the processing of RGB images. The neural network wastested on the VIRAT dataset with annotations for object de-tection, a problem this approach is well suited for. The ac-curacy was found to improve significantly (up to 66%), witha roughly 40% increase in computational time.
|
|
| 3. |
|
|
| 4. |
- Broms, Camilla, et al.
(författare)
-
Combined analysis of satellite and ground data for winter wheat yield forecasting
- 2023
-
Ingår i: Smart Agricultural Technology. - : Elsevier BV. - 2772-3755. ; 3
-
Tidskriftsartikel (refereegranskat)abstract
- We built machine learning and image analysis tools in order to forecast winter wheat yield based on a rich multi dimensional tensor of agricultural information spanning different scales. This information consists of satellite multi-band images, local soil samples obtained from national databases, local weather as well as field data from 23 farms cultivating winter wheat in southern Sweden. This is inherently a large multi-scale problem due to the large temporal and spatial variation of the input data. We aggregate the data on spatially averaged features over grids which temporally span a seasonal timeline from seeding to harvest. Data cleaning is performed through interpolation for satellite images due to cloud obstructions. Furthermore data is heavily imbalanced since the amount of satellite information far exceeds that of the ground data. Data variance therefore can be an issue which we counter by using a decision tree approach. We find that the Light Gradient Boosting decision tree trained on 262 input features is able to predict winter wheat yield with 82% accuracy. Subsequently we employ game theory in order to better understand the relational importance of specific input features towards forecasting yield. Specifically we find that some of the most important features towards the resulting predictions are the percent clay and magnesium in the soil. Similarly the most important features from the satellite data are: a) the NORM index (Euclidean distance of all bands) computed in the second week of April, b) the NORM index computed in the middle of May as well as c) the second spectral band from the last week of June.
|
|
| 5. |
- Nilsson, Mikael, et al.
(författare)
-
Development of automatic surveillance of animal behaviour and welfare using image analysis and machine learned segmentation technique.
- 2015
-
Ingår i: Animal. - 1751-7311 .- 1751-732X. ; 9:11, s. 1859-1865
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper the feasibility to extract the proportion of pigs located in different areas of a pig pen by advanced image analysis technique is explored and discussed for possible applications. For example, pigs generally locate themselves in the wet dunging area at high ambient temperatures in order to avoid heat stress, as wetting the body surface is the major path to dissipate the heat by evaporation. Thus, the portion of pigs in the dunging area and resting area, respectively, could be used as an indicator of failure of controlling the climate in the pig environment as pigs are not supposed to rest in the dunging area. The computer vision methodology utilizes a learning based segmentation approach using several features extracted from the image. The learning based approach applied is based on extended state-of-the-art features in combination with a structured prediction framework based on a logistic regression solver using elastic net regularization. In addition, the method is able to produce a probability per pixel rather than form a hard decision. This overcomes some of the limitations found in a setup using grey-scale information only. The pig pen is a difficult imaging environment because of challenging lighting conditions like shadows, poor lighting and poor contrast between pig and background. In order to test practical conditions, a pen containing nine young pigs was filmed from a top view perspective by an Axis M3006 camera with a resolution of 640×480 in three, 10-min sessions under different lighting conditions. The results indicate that a learning based method improves, in comparison with greyscale methods, the possibility to reliable identify proportions of pigs in different areas of the pen. Pigs with a changed behaviour (location) in the pen may indicate changed climate conditions. Changed individual behaviour may also indicate inferior health or acute illness.
|
|
| 6. |
- Nilsson, Mikael, et al.
(författare)
-
Learning Based Image Segmentation of Pigs in a Pen
- 2014
-
Ingår i: ; , s. 1-4
-
Konferensbidrag (refereegranskat)abstract
- As farms are getting bigger with more animals, less manual supervision and attention can be given the animals on both group and individual level. In order not to jeopardize animal welfare, automated supervision is in some way already in use. Function and control of ventilation is already in use in modern pig stables, e.g. by the use of sensors for temperature, relative humidity and malfunction connected to alarm. However, by measuring continuously directly on the pigs, more information and more possibilities to adjust production inputs would be possible. In this work, the focus is on a key image processing algorithm aiding such a continuous system - segmentation of pigs in images from video. The proposed solution utilizes extended state-of-the-art features in combination with a structured prediction framework based on a logistic regression solver using elastic net regularization. Objective results on manually segmented images indicate that the proposed solution, based on learning, performs better than approaches suggested in recent publications addressing pig segmentation in video.
|
|
| 7. |
- Saunier, Nicolas, et al.
(författare)
-
A Public Video Dataset for Road Transportation Applications
- 2014
-
Konferensbidrag (refereegranskat)abstract
- Video data and the tools for automated analysis have a great potential to be used in road traffic research, particularly road safety. In this project a video dataset is built and made public so that researchers can evaluate their algorithms on it. The dataset focuses on the traffic research applications (data from real research projects) and provides recordings of the traffic scenes, meta-data, camera calibration, ground truth, protocols for comparing algorithms and software tools and libraries for reading/presenting the data. To the authors’ knowledge, this public dataset is the first of its kind. With the proposed dataset, researchers get access to a large variety of recordings representing different traffic, weather and lighting conditions to evaluate and compare different tools and applications. As a consequence, discussions between computer vision and transportation researchers are expected to increase, contributing to more collaborations and better tools, more accurate and user-friendly, to obtain automatically rich traffic data from video.
|
|
