1. |
- Ahlberg, Erik, et al.
(author)
-
"Vi klimatforskare stödjer Greta och skolungdomarna"
- 2019
-
In: Dagens nyheter (DN debatt). - 1101-2447.
-
Journal article (pop. science, debate, etc.)abstract
- DN DEBATT 15/3. Sedan industrialiseringens början har vi använt omkring fyra femtedelar av den mängd fossilt kol som får förbrännas för att vi ska klara Parisavtalet. Vi har bara en femtedel kvar och det är bråttom att kraftigt reducera utsläppen. Det har Greta Thunberg och de strejkande ungdomarna förstått. Därför stödjer vi deras krav, skriver 270 klimatforskare.
|
|
2. |
|
|
3. |
- Ahrnbom, Martin, et al.
(author)
-
Improving a real-time object detector with compact temporal information
- 2018
-
In: 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
-
Conference paper (peer-reviewed)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.
|
|
4. |
- Ahrnbom, Martin, et al.
(author)
-
Real-Time and Online Segmentation Multi-Target Tracking with Track Revival Re-Identification
- 2021
-
In: Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. - : SCITEPRESS - Science and Technology Publications. - 9789897584886 ; 5, s. 777-784
-
Conference paper (peer-reviewed)abstract
- The first online segmentation multi-target tracking algorithm with reported real-time speeds is presented. Based on the popular and fast bounding box based tracker SORT, our method called SORTS is able to utilize segmentations for tracking while keeping the real-time speeds. To handle occlusions, which neither SORT nor SORTS do, we also present SORTS+RReID, an optional extension which uses ReID vectors to revive lost tracks from SORTS to handle occlusions. Despite only computing ReID vectors for 6.9% of the detections, ID switches are decreased by 45%. We evaluate on the MOTS dataset and run at 54.5 and 36.4 FPS for SORTS and SORT+RReID respectively, while keeping 78-79% of the sMOTSA of the current state of the art, which runs at 0.3 FPS. Furthermore, we include an experiment using a faster instance segmentation method to explore the feasibility of a complete real-time detection and tracking system. Code is available: https://github.com/ahrnbom/sorts.
|
|
5. |
- Ardö, Håkan, et al.
(author)
-
Bayesian Formulation of Gradient Orientation Matching
- 2015
-
In: Lecture Notes in Computer Science. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. ; 9163, s. 91-103
-
Conference paper (peer-reviewed)abstract
- Gradient orientations are a common feature used in many computer vision algorithms. It is a good feature when the gradient magnitudes are high, but can be very noisy when the magnitudes are low. This means that some gradient orientations are matched with more confidence than others. By estimating this uncertainty, more weight can be put on the confident matches than those with higher uncertainty. To enable this, we derive the probability distribution of gradient orientations based on a signal to noise ratio defined as the gradient magnitude divided by the standard deviation of the Gaussian noise. The noise level is reasonably invariant over time, while the magnitude, has to be measured for every frame. Using this probability distribution we formulate the matching of gradient orientations as a Bayesian classification problem. A common application where this is useful is feature point matching. Another application is background/foreground segmentation. This paper will use the latter application as an example, but is focused on the general formulation. It is shown how the theory can be used to implement a very fast background/foreground segmentation algorithm that is capable of handling complex lighting variations.
|
|
6. |
- Ardö, Håkan, et al.
(author)
-
Bayesian Formulation of Image Patch Matching Using Cross-correlation
- 2012
-
In: Journal of Mathematical Imaging and Vision. - : Springer Science and Business Media LLC. - 0924-9907 .- 1573-7683. ; 43:1, s. 72-87
-
Journal article (peer-reviewed)abstract
- A classical solution for matching two image patches is to use the cross-correlation coefficient. This works well if there is a lot of structure within the patches, but not so well if the patches are close to uniform. This means that some patches are matched with more confidence than others. By estimating this uncertainty, more weight can be put on the confident matches than those that are more uncertain. To enable this two distribution functions for two different cases are used: (i) the correlation between two patches showing the same object but with different lighting conditions and different noise realisations and (ii) the correlation between two unrelated patches.Using these two distributions the patch matching problem is, in this paper, formulated as a binary classification problem. The probability of two patches matching is derived. The model depends on the signal to noise ratio. The noise level is reasonably invariant over time, while the signal level, represented by the amount of structure in the patch or its spatial variance, has to be measured for every frame.A common application where this is useful is feature point matching between different images. Another application is background/foreground segmentation. This paper will concentrate on the latter application. It is shown how the theory can be used to implement a very fast background/foreground segmentation algorithm by transforming the calculations to the DCT-domain and processing a motion-JPEG stream without uncompressing it. This allows the algorithm to be embedded on a 150 MHz ARM based network camera. It is also suggested to use recursive quantile estimation to estimate the background model. This gives very accurate background models even if there is a lot of foreground present during the initialisation of the model.
|
|
7. |
- Ardö, Håkan, et al.
(author)
-
Bayesian Formulation of Image Patch Matching Using Cross-correlation
- 2009
-
In: 2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC). - 9781424446209 ; , s. 92-99
-
Conference paper (peer-reviewed)abstract
- A classical solution for matching two image patches is to use the cross-correlation coefficient. This works well if there is a lot of structure within the patches, but not so well if the patches are close to uniform. This means that some patches are matched with more confidence than others. By estimating this uncertainty more weight can be put on the confident matches than those that are more uncertain. In this paper we present a system that can learn the distribution of the correlation coefficient from a video sequence of an empty scene. No manual annotation of the video is needed. Two distributions functions are learned for two different cases: i) the correlation between an estimated background image and the current frame showing that background and ii) the correlation between an estimated background image and an unrelated patch. Using these two distributions the patch matching problem is formulated as a binary classification problem and the probability of two patches matching is derived. The model depends on the signal to noise ratio. The noise level is reasonably invariant over time, while the signal level, represented by the amount of structure in the patch or it's spatial variance, has to be measured for every frame. A common application where this is useful is feature point matching between different images. Another application is background/foreground segmentation. In this paper it is shown how the theory can be used to implement a very fast background/foreground segmentation by transforming the calculations to the DCT-domain and processing a motion JPEG stream without uncompressing it. This allows the algorithm to be embedded on a 150MHz ARM based network camera. It is also suggested to use recursive quantile estimation to estimate the background model. This gives very accurate background models even if there is a lot of foreground present during the initialisation of the model.
|
|
8. |
|
|
9. |
- Ardö, Håkan, et al.
(author)
-
Flow Counting Using Realboosted Multi-sized Window Detectors
- 2012
-
In: Computer Vision – ECCV 2012. Workshops and Demonstrations : Florence, Italy, October 7-13, 2012, Proceedings, Part III - Florence, Italy, October 7-13, 2012, Proceedings, Part III. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 1611-3349 .- 0302-9743. - 9783642338847 - 9783642338854 ; 7585, s. 193-202
-
Conference paper (peer-reviewed)abstract
- One classic approach to real-time object detection is to use adaboost to a train a set of look up tables of discrete features. By utilizing a discrete feature set, from features such as local binary patterns, efficient classifiers can be designed. However, these classifiers include interpolation operations while scaling the images over various scales. In this work, we propose the use of real valued weak classifiers which are designed on different scales in order to avoid costly interpolations. The use of real valued weak classifiers in combination with the proposed method avoiding interpolation leads to substantially faster detectors compared to baseline detectors. Furthermore, we investigate the speed and detection performance of such classifiers and their impact on tracking performance. Results indicate that the realboost framework combined with the proposed scaling framework achieves an 80% speed up over adaboost with bilinear interpolation.
|
|
10. |
|
|